Semantic Knowledge Graphs for the News: A Review

ANDREAS L. OPDAHL, University of Bergen, Norway

TAREQ AL-MOSLMI, Independent Researcher, Norway
DUC-TIEN DANG-NGUYEN, MARC GALLOFRÉ OCAÑA, BJØRNAR TESSEM, and
140
CSABA VERES, University of Bergen, Norway

ICT platforms for news production, distribution, and consumption must exploit the ever-growing availability
of digital data. These data originate from different sources and in different formats; they arrive at different
velocities and in different volumes. Semantic knowledge graphs (KGs) is an established technique for integ-
rating such heterogeneous information. It is therefore well-aligned with the needs of news producers and
distributors, and it is likely to become increasingly important for the news industry. This article reviews the
research on using semantic knowledge graphs for production, distribution, and consumption of news. The
purpose is to present an overview of the field; to investigate what it means; and to suggest opportunities and
needs for further research and development.
CCS Concepts: • Computing methodologies → Semantic networks; • Information systems → Inform-
ation systems applications;
Additional Key Words and Phrases: News, journalism, news production, news distribution, news consump-
tion, knowledge graphs, ontology, semantic technologies, Linked Data, Linked Open Data, Semantic Web,
literature review
ACM Reference format:
Andreas L. Opdahl, Tareq Al-Moslmi, Duc-Tien Dang-Nguyen, Marc Gallofré Ocaña, Bjørnar Tessem,
and Csaba Veres. 2022. Semantic Knowledge Graphs for the News: A Review. ACM Comput. Surv. 55, 7, Art-
icle 140 (December 2022), 15 pages.
https://doi.org/10.1145/3543508

1 INTRODUCTION
Journalism relies increasingly on computers and the Internet [114]. Central drivers are the big
and open data sources that have become available on the Web. For example, researchers have
investigated how news events can be extracted from big-data sources such as tweets [108] and
other texts [107] and how big and open data can benefit journalistic creativity during the early
phases of news production [115].

This research is funded by the Norwegian Research Council’s IKTPLUSS programme as part of the News Angler project
(grant number 275872) and by MediaFutures partners and the Research Council of Norway as part of MediaFutures: Re-
search Centre for Responsible Media Technology & Innovation (grant number 309339).
Authors’ addresses: A. L. Opdahl, D.-T. Dang-Nguyen, M. G. Ocaña, B. Tessem, and C. Veres, Department of Informa-
tion Science and Media Studies, University of Bergen, P.O.Box 7802, N-5020 Bergen, Norway; emails: {Andreas.Opdahl,
Duc-Tien.Dang-Nguyen, Marc.Gallofre, Bjornar.Tessem, Csaba.Veres}@uib.no; T. Al-Moslmi, Independent Researcher, Oslo,
Norway; email: tareqmail19@gmail.com.

This work is licensed under a Creative Commons Attribution International 4.0 License.
© 2022 Copyright held by the owner/author(s).
0360-0300/2022/12-ART140
https://doi.org/10.1145/3543508

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:2 A. L. Opdahl et al.

Semantic knowledge graphs and other semantic technologies [83] offer a way to make big and
open data sources more readily available for journalistic and other news-related purposes. They
offer a standard model and supporting resources for sharing, processing, and storing factual know-
ledge on both the syntactic and semantic level. Such knowledge graphs thus offer a way to make
big, open, and other data sources better integrated and more meaningful. They make it possible
to integrate the highly heterogeneous information available on the Internet and to make it more
readily available for journalistic and other news-related purposes.
This article will systematically review the research literature on semantic knowledge graphs in
the past two decades, from the time when the Semantic Web—an important precursor to semantic
knowledge graphs—was first proposed [86]. The purpose is to present an overview of the field; to
investigate what it means; and to suggest opportunities and needs for further research and devel-
opment. We understand both semantic knowledge graphs and the news in a broad sense. Along
with semantic knowledge graphs, we include facilitating semantic technologies such as RDF, OWL,
and SPARQL and their uses for semantically Linked (Open) Data and Semantic Web.1 We also in-
clude all aspects of production, distribution, and consumption of news. More precise inclusion and
exclusion criteria will follow in Section 2.
To the best of our knowledge, no literature review has previously attempted to cover this in-
creasingly important area in depth. Several reviews have been published recently on computa-
tional journalism in its various guises (e.g., References [92, 97, 129, 134]), but none of them go
deeply into the technology in general nor into semantic knowledge graphs in particular. Also, re-
cent overviews of knowledge graphs (e.g., References [93, 99, 104, 106, 121]) do not consider the
specific challenges and opportunities for journalism or the news domain. Among the few papers
that discuss the relation between semantic technologies and news, Reference [125] discusses how
Linked Data can be integrated into and add value to news production processes and value chains in
a non-disruptive way. It presents use cases from dynamic semantic publishing at BBC with atten-
tion to professional scepticism towards technology-driven innovation. More recently, Newsroom
3.0 [120] builds on an international field study of three newsrooms—in Brazil, Costa Rica, and the
UK—to propose a framework for managing technological and media convergence in newsrooms.
The framework uses semantic technologies to manage news knowledge, attempting to support
interdisciplinary teams in their coordination of journalistic activities, cooperative production of
content, and communication between professionals and news prosumers. Transitions in Journal-
ism [124] discusses how new technologies are constantly challenging well-established journalistic
norms and practices, discussing ways in which semantic journalism can exploit semantic techno-
logies for everyday journalism.
Compared to these targeted efforts, this article presents the first systematic review of semantic
knowledge graphs for news-related purposes in a broad sense. We ask the following research
questions:
RQ1: Which research problems and approaches are most common, and what are the central
results?
For example, the different research contributions may produce different types of results; use
different research methods; target different users; focus on different news-related tasks us-
ing different input data; use different semantic and other techniques; and address different
news domains, languages, and phases of the news life-cycle.

1 Hence,the article will use the term “semantic knowledge graph” or “semantic KG” in an inclusive way that also covers
semantic technologies, computational ontology, Linked Open Data (LOD), and Semantic Web.

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:3

RQ2: Which research problems and approaches have received less attention, and what types of
contributions are rarer?
Where are the green fields and other areas where knowledge is limited and further research
needed?
RQ3: How is the research evolving?
Different problems, result types, and approaches may be more or less prominent at different
times, and each of them may be dealt with differently at different times.
RQ4: Which are the most frequently cited papers and projects, and which papers and projects are
citing one another?
For example, how is the research literature organised; which earlier results are cited
most by the main papers; and which main papers are most cited in the broader
literature?
To answer these questions, the rest of the article is organised as follows: Section 2 outlines the
literature-review process. Section 3 reviews the main papers. Section 4 discusses the main pa-
pers, answers the research questions, and offers many paths for further work. Section 5 concludes
the article. The article is supported by an online Addendum that: describes our systematic review
method in further detail; provides additional analyses of the main papers and related papers; and
offers further readings about the resources and tools that are mentioned in the papers we review.
These further readings are marked with an “A” in the main text, for example, “RDFA121 ”.

2 METHOD
To answer our research questions, we conduct a systematic literature review (SLR) [111]. In
line with our aim to present an overview of the field, we review the research literature in
breadth to cover as many salient research problems, approaches, and potential solutions as pos-
sible. A detailed description of our systematic review method is available in the online Addendum
(Section A).
Our review covers research on semantic knowledge graphs for the news understood in a
wide sense. We include papers that use semantic technologies such as RDF,A121 OWL,A117 and
SPARQL,A124 [83] and practices such as Linked (Open) Data [87] and Semantic Web [86], but we
exclude papers that use graph structures only for computational purposes isolated from the se-
mantically linked Web of Data. We also include all aspects of production, distribution, and con-
sumption of news, but we exclude research that uses news corpora only for evaluation purposes.
We search for literature through the five search engines ACM Digital Library,A14 Elsevier
ScienceDirect,A32 IEEE Xplore,A63 SpringerLink,A83 and Clarivate Analytics’ Web of Science.A18 We
also conduct supplementary searches using Google Scholar.A52 We search using variations of the
phrases “knowledge graph,” “semantic technology,” “linked data,” “linked open data,” and “semantic
web” combined with variations of “news” and “journalism” adapted to each search engine’s syntax.
We select peer-reviewed and archival papers published in esteemed English-language journals or
in high-quality conferences and workshops.
The search results are screened in three stages, so each selected paper is in the end considered
by at least three co-authors. In the first stage, we screen search results based on title, abstract, and
keywords. In the second stage, we skim the full papers and also consider the length, type, language,
and source of each paper. In the third stage, we analyse the selected papers in detail according to
the framework described below (Table 1). When several papers describe the same line of work, we
select the most recent and comprehensive report. In the end, more than 6,000 search results are
narrowed down to 80 fully analysed main papers. They are listed near the end of this article, right

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:4 A. L. Opdahl et al.

Table 1. Analysis Framework

Technical result type: What type of technical result does the paper present (e.g., pipelines/prototypes, industrial platforms,
algorithms, or information resources such as ontologies and knowledge graphs)?
Empirical result type: Which research methods are used (e.g., experiments, case studies, or industrial testing)?
Intended users: Who are the intended users or direct benefactors of the research result (e.g., the general news users,
journalists, archivists, or knowledge workers in general)?
Task: What kind of news-related tasks does the research attempt to support or improve (e.g., semantic
annotation, event detection, relation extraction, or content retrieval, provision, and enrichment)?
Input data: Which sources and types of input data are used (e.g., digital news articles, social media messages, or
multimedia news)?
News life cycle: Which phases of the news cycle are targeted (e.g., future news, emerging news, breaking news,
developing news, or already published news)?
Semantic techniques: Which semantic resources, techniques, and tools are used to create, manage, and exploit semantic
knowledge graphs (including information exchange standards, ontologies and vocabularies, semantic
data resources, and processing and storage techniques)?
Other techniques: Which other computing techniques and standards are used in combination with semantic knowledge
graphs, including news standards and techniques for natural-language processing (NLP), machine
learning (ML), and deep learning (DL)?
News domain: Does the research target a specific news domain (e.g., economy/finance, the environment, or education)?
Language and region: Does the research focus on a specific language or combination of languages?

before the Reference list, and we distinguish them from other references by the letter “M,” e.g.,
[37].
Through a pilot study, we establish an analysis framework that we continue to revise and refine
as the analysis progresses [90]. Table 1 lists the 10 top-level themes in the final framework, along
with examples of sub-themes that we use to describe and compare the main papers in Section 3.
For example, many main papers address specific groups of intended users. Intended users therefore
becomes a top-level theme in our framework, with more specific groups of users, such as journalists,
archivists, and fact checkers, as sub-themes.
We make the detailed paper analyses along with their metadata available as a semantic know-
ledge graph through a SPARQL endpoint at http://bg.newsangler.uib.no. To support impact ana-
lysis, the metadata includes all incoming and outgoing citations of and by our main papers. The
complete graph contains information about 4,238 papers, 9,712 authors, and 699 topics from Se-
mantic Scholar.A36 The online Addendum (Section A) provides further details and presents ex-
amples of SPARQL queries that can be used to explore the graph (Table 10).

3 REVIEW OF MAIN PAPERS

This section reviews the 80 main papers according to the themes of Table 1. Our review and dis-
cussion is based on careful manual reading, analysis, marking, and discussion of the main papers,
organised by the evolving themes and sub-themes in our analysis framework.

3.1 Technical Result Types

As shown in Figure 1(a), the main papers present a wide variety of technical research results.
Further details are available in Table 6.
Pipelines and prototypes: A clear majority of main papers develop ICT architectures and tools
for supporting news-related information processing with semantic knowledge graphs and related
techniques. Most common are research prototypes and experimental pipelines. For example, the
Knowledge and Information Management (KIM) platform [37] is an early and much-cited in-
formation extraction system that annotates and indexes named entities found in news documents
semantically and makes them available for retrieval. To allow precise ontology-based retrieval,
each identified entity is annotated with both a specific instance in an extensive knowledge base
and a class defined in the associated KIM Ontology (KIMO).2 Which defines around 250 classes and

2 Later superseded by the PROTON ontology.A1

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:5

Fig. 1. The most frequent (a) technical and (b) empirical result types.

100 attributes and relations. The platform offers a graphical user interface for viewing, browsing
and performing complex searches in collections of annotated news articles. Another early initiat-
ive is the News Engine Web Services (NEWS) project [15], which presents a prototype that auto-
matically annotates published news items in several languages. The aim is to help news agencies
provide fresh, relevant, and high-quality information to their customers. NEWS uses a dedicated
ontology (the NEWS Ontology [17]) to facilitate semantic search, subscription-based services, and
news creation through a web-based user interface. Hermes [4] supplies news-based evidence to
decision-makers. To facilitate semantic retrieval, it automatically identifies topics in news articles
and classifies them. The topics and classes are defined in an ontology that has been extended with
synonyms and hypernyms from WordNet [98, 117] to improve recall.
Production systems: Some main papers take one step further and present industrial platforms
that have run in news organisations, either experimentally or in production. The earliest example
is AnnoTerra [57], a system developed by NASA to enhance earth-science news feeds with content
from relevant multimedia data sources. The system matches ontology concepts with keywords
found in the news texts to identify data sources and support semantic searches. Also, Reference
[130] reports industrial experience with NEWS at EFE, a Spanish international news agency. The
most recent example is VLX-Stories [14], a commercial, multilingual system for event detection
and information retrieval from media feeds. The system harvests information from online news
sites; aggregates them into events; labels them semantically; and represents them in a knowledge
graph. The system is also able to detect emerging entities in online news. VLX-Stories is deployed
in production in several organisations in several countries. Each month, it detects over 9,000 events
from over 4,000 news feeds from seven different countries and in three different languages, extend-
ing its knowledge graph with 1,300 new entities as a side result.
System architectures: Whether oriented towards research or industry, another group of papers
proposes system architectures. The World News Finder [34] presents an architecture that is rep-
resentative of many systems that exploit KGs for managing news content. Online news articles
in HTML format are parsed and analysed using GATE (General Architecture for Text Engin-
eering)A92 and ANNIE (A Nearly New Information Extraction system)A91 with the support
of JAPE (Java Annotations Pattern Engine)A93 rules and ontology gazetteering lists. A do-
main ontology is then used in combination with heuristic rules to annotate the analysed news
texts semantically. The annotated news articles are represented in a metadata repository and made
available for semantic search through a GUI.
Algorithms: Another group of papers focuses on developing algorithms that exploit semantic
knowledge graphs and related techniques, usually supported by proof-of-concept prototypes that

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:6 A. L. Opdahl et al.

are also used for evaluation. Inspired by Google’s PageRank algorithm,A25 Reference [16] proposes
the IdentityRank algorithm for named entity disambiguation in the NEWS project [15]. IdentityR-
ank dynamically adjusts its weights for ranking candidate instances based on news trends (the
frequency of each instance in a period of time) and semantic coherence (the frequency of the
instance in a certain context), and it can be retrained based on user feedback and corrections. Ref-
erence [54] takes trending entities in news streams as its starting point and attempts to identify
and rank other entities in their context. The purpose is to represent trends more richly and un-
derstand them better. One unsupervised and one supervised algorithm are compared. The un-
supervised approach uses a personalised version of the PageRank algorithmA25 over a graph of
trending and contextual entities. The edges encode directional similarities between the entities
using embeddings from a background knowledge graph. The supervised, and better performing,
approach uses a selection of hand-crafted features along with a learning-to-rank (LTR) model,
LightGBM.A79 The selected features include positions and frequencies of the entities in the input
texts, their co-occurrences and popularity, coherence measures based on TagMeA90 and on entity
embeddings, and the entities’ local importance in the text (or salience). NewsLink [75] processes
news articles and natural-language (NL) queries from users in the same way, using standard
natural-language processing (NLP) techniques. Co-occurrence between entities in a news art-
icle or query is used to divide it into segments, for example, corresponding to sentences. The en-
tities in each segment are mapped to an open KG from which a connected sub-graph is extracted
to represent the segment. The sub-graphs are then merged to represent the articles and queries as
KGs that can be compared for similarity to support more robust and explainable query answering.
Hermes also provides an algorithm (to be presented later) for ranking semantic search results [25].
Neural-network architectures: Rather than proposing algorithms, many recent main papers in-
stead exploit semantic knowledge graphs for news purposes using deep neural-network (NN)
architectures. These papers, too, are supported by proof-of-concept prototypes, which are usually
evaluated using gold-standard datasets and information retrieval (IR) metrics. Heterogeneous
graph Embedding framework for Emerging Relation detection (HEER) [79] detects emerging
entities and relations from text reports, i.e., new entities and relations in the news that have so far
not been included in a knowledge graph. The challenges addressed are that new entities and rela-
tions appear at high speed, with little available information at first and without negative examples
to learn from. HEER represents incoming news texts as graphs based on entity co-occurrence and
incrementally maintains joint embeddings of the news graphs and an open knowledge graph. The
result is positive and unlabelled (PU) entity embeddings that are used to train and maintain a
PU classifierA31 that detects emerging relations incrementally.
Context-Aware Graph Embedding (CAGE) [66] is an approach for session-based news re-
commendation. Entities are extracted from input texts and used to extract a sub-knowledge graph
from an open knowledge graph (the paper uses WikidataA47 ). Knowledge-graph embeddings are
calculated from the sub-knowledge graph, whereas pre-trained word embeddings and Convolu-
tional Neural Networks (CNNs) [102] are used to derive content embeddings from the corres-
ponding input texts. The knowledge-graph and content embeddings are concatenated and com-
bined with user embeddings and refined further using CNNs. Finally, an Attention Neural Net-
work (ANN) [135] on top of Gated Recurrent Units (GRUs) [102] are used to recommend
articles from the resulting embeddings, taking short-term user preferences into account.
Deep Triple Networks (DTN) [42] use a deep-network architecture for topic-specific fake
news detection. News texts are analysed in two ways in parallel: The first way is to use
word2vec [116] embeddings and self-attention [135] on the raw input text. The second way is
to extract triples from the text and analyse them using TransD [110] graph embeddings, attention
and a bi-directional LSTM (Long Short-Term Memory) [102]. A CNN is used to combine the

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:7

results of the two parallel analyses into a single output vector. Background knowledge has been
infused into the second way by training the TransD graph embeddings, not only on the triples ex-
tracted from the input text, but also on related triples from a 4-hop DBpedia [85] extract. Maximum
and average biases from the graph triples are concatenated with the CNN output vector and used
to classify news texts as real or fake. The intuition behind this and other bias-based approaches to
fake news detection is that, if the input text is false, triples learned only from the input text will
have smaller bias than triples learned from the same text infused with true (and thus conflicting)
real-world knowledge.
Ontologies: Almost half the papers include a general or domain-specific ontology for creating
and managing other semantic knowledge graphs. For example, the NEWS project uses OWL to rep-
resent the NEWS Ontology [17], which standardises and interconnects the semantic labels used
to annotate and disseminate news content. The Semantics-based Pipeline for Economic Event
Detection (SPEED) [24] uses a finance ontology represented in OWL to ensure interoperability
between and reuse of existing semantic and NLP solutions. Reference [71] represents the IPTC
(International Press Telecommunications Council) News CodesA68 as SKOSA123 concepts in
an OWL ontology and discusses its uses for semantic enrichment and search. The Evolution-
ary Event Ontology Knowledge (EEOK) ontology [45] represents how different types of news
events tend to unfold over time. The ontology is supported by a pipeline that mines event-evolution
patterns from natural-language news texts that report different stages of the same macro event (or
storyline). The patterns are represented in OWL and used to extract and predict further events in
developing storylines more precisely.
Knowledge graphs: A few papers even present a populated, instance-level semantic knowledge
graph or other linked knowledge base as a central result. For example, K-Pop [36] populates a se-
mantic knowledge graph for enriching news about Korean pop artists. The purpose is to provide
comprehensive profiles for singers and groups, their activities, organisations, and catalogues. As an
example application, the resulting entertainment KG is used to power Gnosis, a mobile application
for recommending K-Pop news articles. CrimeBase [67] presents a knowledge graph that integ-
rates crime-related information from popular Indian online newspapers. The purpose is to help
law enforcement agencies analyse and prevent criminal activities by gathering and integrating
crime entities from text and images and making them available in machine-readable form. Claim-
sKG [69] is a live knowledge graph that represents more than 28,000 fact-checked claims published
since 1996, totalling over 6 million triples. It uses a semi-automatic pipeline to harvest fact checks
from popular fact-checking websites; annotate them with entities from DBpedia; represent them
in RDFA121 according to a semantic data model in RDFSA122 ; normalise the validity ratings; and
resolve co-references across claims. Reference [12] uses hashtags and other metadata associated
with tweets and tweeters to build an RDF model of over 900,000 French political tweets, totalling
more than 20 million triples that describe facts, statements, and beliefs in time. The purpose is to
trace how actors propagate knowledge—as well as misinformation and hearsay—over time.
Formal models: A small final group of papers proposes formal models of various types and for
different purposes. For example, Reference [22] presents a formal model for managing inconsist-
encies that arise when live news streams are represented incrementally using description logic. A
trust-based algorithm for belief-base revision is presented that takes users’ trust in information
sources into account when choosing which inconsistent information to discard.
Summary: Our review suggests that the most common types of results are pipelines and proto-
types. In addition, many papers propose ontologies, system architectures, algorithms, and neural-
network architectures. A few papers also introduce new knowledge graphs. There has been a shift
in recent years from research on algorithms and system architectures towards papers that propose
deep neural-network architectures. A few of those recent papers also mention explainability.

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:8 A. L. Opdahl et al.

3.2 Empirical Result Types

As shown in Figure 1(b), a large majority of the papers include an empirical evaluation of their
technical proposals.
Experiments: As shown in the previous section, a majority of papers develop pipelines or proto-
types, which are then evaluated empirically. The most common evaluation method is controlled
experiments using gold-standard datasets and information retrieval (IR) measures such as pre-
cision (P), recall (R), and accuracy (A). For example, KOPRA [70] is a deep-learning approach
that uses a Graph Convolutional Network (GCN) [91, 103] for news recommendation. An ini-
tial entity graph (called interest graph) is created for each user from entities mentioned in the news
titles and abstracts of that user’s short- and long-term click histories. A joint knowledge pruning
and Recurrent Graph Convolution (RGC) mechanism is then used to augment the entities in
the interest graph with related entities from an open KG. Finally, entities extracted from candidate
news texts are compared with entities in the interest graphs to predict articles a user may find in-
teresting. The approach is evaluated experimentally with Wikidata as the open KG and using two
standard datasets (MIND and Adressa). RDFLiveNews [21] aims to represent RSS data streamsA22
as RDF triples in real time. Candidate triples are extracted from individual RSS items and clustered
to suggested output triples. Components of the approach are evaluated in two ways. The first way
measures RDFLiveNews’ ability to disambiguate alternative URIs for named entities detected in
the input items. Disambiguation results are evaluated against a manually crafted gold standard
using precision, recall, and F1 metrics and by comparing them to the outputs of a state-of-art NED
tool (AIDAA59 ). The second way measures RDFLiveNews’ ability to cluster similar triples extracted
from different RSS items. The clusters are evaluated against the manually crafted gold standard
using sensitivity (S), positive predictive value (PPV), and their geometric mean.
Performance evaluation: A smaller number of experimental papers collect performance measures
such as execution times and throughput in addition to or instead of IR measures. For example, the
scalability of RDFLiveNews [21] is also measured using run times for different components of the
approach on three test corpora. The results suggest that, with some parallelisation, it is able to
handle at least 1,500 parallel RSS feeds. The performance of KnowledgeSeeker [39], an ontology-
based agent system for recommending Chinese news articles, is measured through execution times
on three datasets for a given computer configuration and using the performance of a vanilla TF-
IDF-based approach as comparison baseline. The throughput of SPEED [24] is benchmarked on a
corpus of 200 news messages extracted from Yahoo!’s business and technology news feeds.A126
Ablation, explainability, and parameter studies: Many recent papers also include ablation stud-
ies [54, 66, 70, 75], explainability studies [45, 70, 75], and parameter and sensitivity studies [79].
A common theme is that they all use deep or other machine learning techniques. We will present
more examples later (e.g., References [19, 40, 73, 74, 78, 80]).
Industrial testing: A few papers present case studies or experience reports from industry. We
have already mentioned the commercial VLX-Stories [14] system. Reference [44] extends the news
production workflow at VRT (Vlaamse Radio- en Televisieomroep), a national Belgian broad-
caster, to support personalised news recommendation and dissemination via RSS feeds. A semantic
version of the IPTC’s NewsML-G2A72 standard is proposed as a unifying (meta-)data model for dy-
namic distributed news event information. As a result, RDF/OWL and NewsML-G2 can be used in
combination to automatically categorise, link, and enrich news-event metadata. The system has
been hooked into the VRT’s workflow engine, facilitating automatic recommendation of devel-
oping news stories to individual news users. Reference [68] semantically enriches the content of
archival news texts. The proposed system identifies mentions of named entities along with their
contexts; links the contextualised mentions to entities in a knowledge base; and uses the links

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:9

to retrieve further relevant information from the knowledge base. The system has been deployed
and applied to 10 years of archival news in a local Italian newspaper. And as already mentioned, a
prototype of the NEWS system [15] has run experimentally at EFE, alongside their legacy produc-
tion system, introducing a semi-automatic workflow that lets journalists validate the annotations
suggested by the system [130].
Case studies and examples: Other papers present realistic examples based on industrial experi-
ence. For example, the MediaLoep project [10] (involving many of the authors behind Reference
[44], and Reference [9], to be presented later) discusses how to improve retrieval and increase re-
use of previously broadcast multimedia news items at VRT, the national Belgian broadcaster, both
as background information and as reusable footage. The paper reports experiences with collecting
descriptive metadata from different news production systems; integrating the metadata using a
semantic data model; and connecting the data model to other semantic data sets to enable more
powerful semantic search.
Proof-of-concept demonstrations and use cases: Similar types of qualitative evaluations, but with
less focus in industrial-scale examples, are proof-of-concept demonstrations and hypothetical use
cases (e.g., Reference [65]).
User studies: A final group of papers presents user studies and usability tests. Reference [76] rep-
resents news articles as small knowledge graphs enriched with word similarities from Word-
Net [98, 117]. Overlaps between the sub-graphs of new articles and of articles a user has found
interesting in the past are used to recommend new articles to the user. Sub-graphs are compared us-
ing Jaccard similarity. The approach is evaluated on a collection of Japanese news articles. Twenty
users were asked to rate suggested articles in terms of relevance and of interest, breaking the latter
down into curiosity and serendipity.
Summary: Our review shows that experimental evaluation of proposed pipelines/prototypes is
the most used research method. Experiments most often use information retrieval measures, but
usability and performance measures are also employed. In recent years, experiments are increas-
ingly often supplemented by studies of ablation, explainability, and parameter selection. Other
used research methods are industrial testing, case studies and examples, proof-of-concept demos,
use cases, and user studies.

3.3 Intended Users

The most frequent types of intended users—or immediate beneficiaries—of the results from our
main papers are shown in Figure 2(a).
News users: More than half the main papers aim to offer news services to the general public. An
early example is Rich News [11], a system that automatically transcribes and segments radio and
TV streams. Key phrases extracted from each segment are used to retrieve web pages that report
the same news event. The web pages are annotated semantically using the KIM platform [37],
whose web interface is used to support searching and browsing news stories semantically by topic
and playing the corresponding segments of the associated media files.
Journalists, newsrooms, and news agencies: The second largest group of papers aims to sup-
port journalists and other professionals in newsrooms and news agencies. Several projects men-
tioned already belong to this type, including the NEWS project [15]. The proposals in References
[10, 45, 54, 71] also target journalists and other news professionals. The ambition of the News
Angler project [46] is to enable automatic detection of newsworthy events from a dynamically
evolving knowledge graph by representing news angles, such as “proximity,” “nepotism,” or “fall
from grace” [123], formally using Common Logic.A37
Knowledge-base maintainers: Rather than supporting news users directly, some papers support
knowledge-base maintainers on a technical level. For example, Reference [17] presents a plugin

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:10 A. L. Opdahl et al.

Fig. 2. The most frequently (a) intended users and (b) their tasks.

for maintaining the NEWS ontology. Aethalides [58] extends the Hermes framework [4] with a
pipeline for semantic classification using concepts defined in a domain ontology.
Archivists: A smaller group of papers targets archivists, who maintain knowledge bases on the
content level. For example, Neptuno [7] is an early semantic newspaper archive system that aims
to give archivists and reporters richer ways to describe and annotate news materials and to give
reporters and news readers better search and browsing capabilities. It uses an ontology for clas-
sifying archive content along with modules for semantic search, browsing, and visualisation. The
purpose of the formal model for belief-base revision [22] presented earlier is also to maintain
knowledge bases by detecting and resolving inconsistencies.
Fake-news detectors and fact checkers: Several recent papers focus on supporting fake-news detect-
ors and fact checkers. We have already mentioned Deep Triple Networks (DTN) [42]. Reference
[5] detects fake news through a hybrid approach that assesses sentiments, entities, and facts extrac-
ted from news texts. ClaimsKG [69], the large knowledge graph of French political tweets, can be
used to trace how knowledge—along with misinformation and hearsay—is propagated over time.
Several of the recent deep-NN approaches we will present later also target fake-news detection
and fact checking.
Knowledge workers: A smaller group of papers targets general knowledge workers and inform-
ation professionals outside the news profession. For example, KIM [37] aims to improve news
browsing and searching for knowledge workers in general. Other papers aim to support specific
information professions. The Automatic Georeferencing Video (AGV) pipeline [13] makes news
videos from the RAI archives available for geography education. Audio is extracted from video us-
ing ffmpegA4 and transcribed using Ants.A3 Apache OpenNLPA46 is used to extract named entities
mentioned in the video segment. Google’s Knowledge Graph is used to add representative images
and facts about related people and places. The places are in turn used to make the videos and their
metadata available through Google Street MapA54 -based user interfaces. The pipeline is tested on
a dataset of 10-minute excerpts from 6,600 videos from a thematic RAI newscast (Leonardo TGR).
AnnoTerra [57] uses ontologies and semantic search to improve NASA’s earth-science news feeds,
targeting both experts and inexperienced users of earth-science data. CrimeBase [67] uses rules to
extract entities from text and associated image captions in multimodal crime-related online news.
The extracted entities are correlated using contextual and semantic similarity measures, whereas
image entities are correlated using image features. The resulting knowledge base uses an OWL on-
tology to integrate crime-related information from popular Indian online newspapers. Other main
papers (to be presented later) target professionals in domains such as economy and finance [51],
environmental communication [63], and medicine [23].

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:11

Summary: Our review indicates that the most frequently intended users (or beneficiaries) of the
main-paper proposals are general news users and journalists. Other intended users/beneficiaries
are newsrooms, knowledge-base maintainers, archivists, fake-news detectors and fact checkers,
and different types of knowledge workers.

3.4 Tasks
As shown in Figure 2(b), the main papers target a wide range of news production, dissemination,
and consumption activities, such as search, recommendation, categorisation, and event detection.
Semantic annotation: Many of the earliest approaches focus on adding semantic labels to entit-
ies and topics mentioned in published news texts. We have already introduced KIM [37], which
labels named entities found in news items with links to instances in a knowledge base and to
classes defined in the KIM Ontology (KIMO). We have also introduced NEWS [15], which an-
notates news items with named entities linked to external sources such as Wikipedia,A49 ISO
country codes,A38 NASDAQ company codes (e.g., Reference [34]), the CIA World Factbook,A27
and SUMO/MILO.A84 It also categorises the news items by content and represents news metadata
using standards and vocabularies such as the Dublin Core (DC)A29 vocabulary, the IPTC’s News
Codes,A68 the News Industry Text Format (NITF),A71 NewsML,A72 , and PRISM—the Publish-
ing Requirements for Industry Standard Metadata.A114
Enrichment: A smaller group of papers instead focuses on enriching annotated news items with
Linked Open Data or information from other semantically labelled sources. For example, Refer-
ence [2] extends the life of TV content by integrating heterogeneous data from sources such as
broadcast archives, newspapers, blogs, social media, and encyclopedia and by aligning semantic
content metadata with the users’ evolving interests. AGV [13] annotates TV news programs with
geographical entities to make archival video content available through a map-based user interface
for educational purposes. In addition to representing the IPTC News Codes using SKOS, Refer-
ence [71] discusses how multimedia news metadata can be augmented using natural-language and
multimedia analysis techniques and enriched with Linked Data, such as facts from DBpedia [85]
and GeoNames.A51 Contributions that represent news texts as sub-graphs of open KGs such as
Wikidata (e.g., CAGE [66], KOPRA [70], and NewsLink [75]) can also be considered enrichment
approaches. We will present a few similar approaches later [40, 80].
Content retrieval: Other papers use semantic annotations (or “semantic footprints”) to support
on-demand (“pull”) or proactive (“push”) dissemination of news content. On the retrieval (on-
demand, pull) side, a clear majority of the main papers support tasks such as searching for and
otherwise retrieving news items. Projects such as KIM [37], NEWS [15], and Hermes [4] all have
content provision as central tasks. The Hermes Graphical Query Language (HGQL) [25] makes
it simpler for non-expert users to search semantically for content available in the Hermes frame-
work. It is based on RDF-GL,A61 a SPARQL-based graphical query language for RDF, and also
provides an algorithm for ranking search results. The World News Finder [34] uses a World News
Ontology along with heuristic rules to automatically create metadata files from HTML news doc-
uments to support semantic user queries. The aim of NewsLink [75] is to support more robust as
well as explainable query answering.
Content provision: On the provision (proactive, push) side, another large group of papers focuses
on actively propagating news to users. For example, Reference [33] aims to provide more accurate
content-based recommendations. It uses existing tools for entity discovery and linking to represent
news messages as sub-graphs by adding edges from Freebase.A2 A new human-annotated data set
(CNREC) for evaluating content-based news recommendation systems is made available and used
to evaluate the approach. Reference [6] aims to deal with data sparsity and cold-start issues in
news recommender systems. It enriches semantic representations of news items and of users with

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:12 A. L. Opdahl et al.

Linked Data to provide more input to recommendation algorithms. Focusing on the user-profiling
(or personalisation) side of news recommendation, Reference [26] uses semantic annotations of
news videos to profile users’ evolving information needs and interests to recommend the most
suitable news stories. Context-Aware Graph Embedding (CAGE) [66] focuses on providing
session-based recommendations, whereas KOPRA [70] aims to take both users’ short- and long-
term behaviours into account.
Event detection: Several more recent approaches go beyond semantic labelling and enrichment
of news content, attempting to extract events or relations (triples, facts) from news items to repres-
ent their meaning on a fine-grained level. NewsReader [72] is a cross-lingual system (or “reading
machine”) that is designed to ingest high volumes of news articles and represent them as Event-
Centric Knowledge Graphs (ECKGs) [59]. Each graph describes an event, and perhaps how it
develops over time, along with the actors and other entities involved in the event. The graphs are
connected through shared entities and temporal overlaps, and the entities are linked to background
information in knowledge bases such as DBpedia. The ASRAEL project [60] maps events described
in unstructured news articles to structured event representations in Wikidata,A47 which are used
to enrich the representations of the articles. Because Wikidata’s event hierarchy is considered too
fine-grained for use in search engines, a hierarchical clustering step follows, after which the more
coarsely categorised events are made available for querying and navigation through an event-
oriented knowledge graph. To keep the Hermes [4] knowledge base up to date, Reference [64] rep-
resents lexico-semantic patterns and associated actions as rules that are used to semi-automatically
detect and semantically describe news events. The approach is implemented in the Hermes News
Portal (HNP), a realisation of the Hermes framework that lets news users browse and query for
relevant news items. The Evolutionary Event Ontology Knowledge (EEOK) ontology [45]
aims to support event detection by suggesting which event types to look for next in a developing
storyline. Reference [38] identifies and reconciles named events from news articles and represents
them in a semantic knowledge graph according to textual contents, entities, and temporal ordering.
The commercial tool VLX-Stories [14] also detects events in media feeds.
Relation extraction: Other papers instead focus on relation extraction, detecting triples (or facts)
that can be used to build new or update existing RDF graphs. An early proposal for deeper text ana-
lysis is SemNews [30], which extracts textual-meaning representations (TMRs) from RSSA22
news items using the OntoSem tool (see, e.g., Reference [33]), which represents each text as a set of
facts about: which actions that are described in the text; which agents, locations, and themes each
action involves; and any temporal relations between the actions. The SemNews tool transforms
the TMRs into OWL to support semantic searching, browsing, and indexing of RSS news items. It
also powers an experimental web service that provides semantically annotated news items along
with news summaries to human users. BKSport [49] automatically annotates sports news using
language-pattern rules in combination with a domain ontology and a knowledge base built on top
of the KIM platform [37]. The tool extracts links and typed entities as well as semantic relations
between them. It also uses pronoun recognition to resolve co-references. Reference [55] repres-
ents the sentences in a news item as triples, analysing not only top-level but also subordinate
clauses. The triples are run through a pipeline of natural language tools that fuse and prioritise
them. Finally, selected triples are used to summarise the underlying event reported in the news
item. Reference [18] identifies novel statements in the news, building on ClausIE and DBpedia to
propose a semantic novelty measure that takes individual user-relevance into account.
Sub-graph extraction: An alternative to extracting relations from news texts is to represent texts
by sub-graphs extracted from open knowledge graphs. An early example is Reference [33], which
uses standard techniques to discover and link entities and adds edges from Freebase to represent

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:13

news messages as sub-graphs to support content-based news recommendation. AnchorKG [40]

represents news articles as small anchor graphs, which consist of entities that are prominently
mentioned in the news text, along with relations between those entities taken from an open know-
ledge graph, and along with those entities’ k-hop neighbourhoods in the graph. One aim is to
improve news recommendation by making real-time knowledge reasoning scalable to large open
knowledge graphs. Another aim is to support explainable reasoning about similarity. Reinforce-
ment learning is used to train an anchor-graph extractor jointly with a news recommender, us-
ing already recognised and linked named entities as inputs. The approach is evaluated using the
MINDA80 dataset and a private dataset extracted from Bing NewsA78 with Wikidata as reference
graph. CAGE [66] represents news texts as sub-graphs extracted from an open reference know-
ledge graph to support session-based news recommendation. KOPRA [70] extracts an entity graph
(called interest graph) for each user from seed entities that are mentioned in the news titles and
abstracts in the user’s short- and long-term click histories. NewsLink [75] represents both news
articles and user queries as small KGs that can be compared for similarity.
KG updating: Several recent contributions use deep and other machine-learning techniques
to keep evolving knowledge graphs up-to-date by identifying new (emerging, dark) entities and
new (or emerging) relations between (the new or existing) entities. We have already mentioned
HEER [79]. PolarisX [77] automatically expands language-independent knowledge graphs in real
time with representations of new events reported by news sites and on social media. It uses a rela-
tion extraction model based on pre-trained multilingual BERT [96] to detect new relations. Chal-
lenges addressed are that available reference knowledge graphs have limited size and scope and
that existing techniques are not able to deal with neologisms based on human common sense. Text-
Aware MUlti-RElational learning method (TAMURE) [78] also extends a knowledge graph
with relations that emerge in the news. It addresses the source heterogeneity of structured know-
ledge graphs and unstructured news texts by learning joint embeddings of entities, relations, and
texts using tensor factorisation implemented in TensorFlow.A13 TAMURE is linear in the number
of parameters, making it suitable for large-scale KGs and live news streams. Reference [61] em-
pirically investigates the prevalence of entities in online news feeds that cannot be identified by
DBpedia Spotlight or by Google’s Knowledge Graph API.A53 Out of 13,456 named entities in an
RSS sample, 378 were missing from DBpedia, 488 were missing from Google’s Knowledge Graph,
and 297 were missing from both.
Ontology development: In various ways, several main papers support ontology development.
Early projects such as KIM [37] and NEWS [15] focus on developing new domain ontologies,
whereas Reference [37] integrates existing IPTC standards and vocabularies into the LOD cloud.
More recent efforts, such as Reference [45], use machine learning techniques to automate ontology
creation and maintenance.
Fake-news detection and fact checking: Several recent papers focus on the detection of fake news,
such as Reference [5]. Another proposal is Reference [52], which uses graph embeddings of news
texts to identify fake news. Reference [48] presents a multimodal approach to quantify whether
real-world news texts and their associated images represent the same or connected entities, sug-
gesting that low coherence is a possible indicator of fake news. Reference [23] lifts medical in-
formation from non-trusted sources into semantic form using FRED [101] and reasons over the
resulting description logic representations using RacerA88 and HermiT.A89 Reasoning inconsisten-
cies are taken to indicate potential “medical myths” that are verbalised and presented to human
agents along with an explanation of the inconsistency. KLG-GAT [80] uses an open knowledge
graph to enhance fact checking and verification. Constituency parsing is used to find entity men-
tions in the claims, which are used to retrieve relevant Wikipedia articles as potential evidence. A

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:14 A. L. Opdahl et al.

BERT-based sentence retrieval model is then used to select the most relevant evidence for the claim.
TagMe is used to link entities in the claims and in the evidence sentences to the Wikidata5MA56
subset of Wikidata and extract triples whose entities are mentioned in the claim and/or evidence.
The triples are further ranked using a BERT-based learning-to-rank (LTR) model. High-ranked
triples are used to construct a graph of the central claim, its potential evidence sentences, and
triples that connect the claim to the evidence sentences. A two-level multi-head graph attention
network is used to propagate information between the claim, evidence, and knowledge (triple)
nodes in the graph as input to a claim classification layer.
Content generation: Targeting news content generation, Tweet2News [3] extracts RDF triples
from documentary (headline-like) tweets using the IPTC’s rNews vocabulary,A69 organises them
into storylines, and enriches them with Linked Open Data to facilitate news generation in addition
to retrieval. The Pundit algorithm [56] even suggests plausible future events based on descriptions
of current events. Structured representations of news titles are extracted from a large historical
news archive that covers more than 150 years, and a machine-learning algorithm is used to ex-
tract causal relations from the structured representations. Although the authors do not propose
specific journalistic uses of Pundit, their algorithm might be used in newsrooms to anticipate al-
ternative continuations of developing events. Reference [31] aims to auto-generate human-quality
news image captions based on a corpus of news texts with associated images and captions. Each
news image is represented as a feature vector using a pre-trained CNN, and each corresponding
article text is split into sentences containing named entities that are processed further in two ways.
One line of analysis enriches the sentences and entities with related information from DBpedia.
Another line instead replaces the named entities with type placeholders, such as PERSON, NORP,
LOC, ORG, and GPE, producing generic sentences that are compressed using dependency parsing
and represented as TF-IDF weighted bags-of-words. Correlations are then established between
the generic-sentence representations and the features of the associated images in the corpus. An
LSTM model is trained to generate matching caption templates for images on top of the pre-trained
CNN. Finally, the semantically enriched original sentences are used to fill in individual entities for
the type placeholders. The approach is evaluated on two public datasets, Good NewsA21 (466K
examples) and Breaking NewsA100 (110K examples), that include news images and captions along
with article texts. Reference [55] (presented earlier) uses the triples that have been extracted, fused,
and prioritised from news sentences to generate new sentences that summarise the underlying
news events. The News Angler project [46] represents news angles to support automatic detection
of newsworthy events from a knowledge graph.
Prediction: Prediction is the focus of a small group of papers that includes Pundit [56] and
EEOK [45]. To predict stock prices, EKGStock [41] uses named-entity recognition and relation
extraction to represent news about Chinese enterprises as knowledge graphs. Embeddings of the
enterprise-specific graphs are then used to estimate connectedness between enterprises. Senti-
ments of news reports that mention an enterprise are then fed into a Gated Recurrent Unit
(GRU) [102] model that predicts stock prices, not only for the mentioned enterprise, but also for
its semantically related ones. Recent predictive approaches include deep-neural network-based
recommendation papers, such as Reference [73] (more later), that are trained to predict click-
through rates (CTR).
Other tasks: In addition to these most frequent uses of knowledge graphs for news, several main
papers address semantic similarity. For example, Reference [35] uses information extraction tech-
niques to automatically annotate news documents semantically to facilitate cross-lingual retrieval
of documents with similar annotations. Reference [9] clusters semantic representations to detect
how news items are derived from one another, using the PROV-O ontologyA120 to represent the res-
ults semantically. Supporting visualisation, the Visualizing Relations Between Objects (VRBO)

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:15

Fig. 3. The most frequent types of (a) input data used and (b) news life-cycle phases targeted.

framework [32] uses semantic and statistical methods to identify temporal patterns between en-
tities mentioned in economic news. It uses the patterns to create and visualise news alerts that
can be formalised and used to manage equity portfolios. Neptuno [7] uses visualisation on the
ontology level to show and publish how knowledge-base concepts are organised. Archiving and
general information organisation is a central task of Neptuno [7] and several other main papers.
Interoperability and data integration is the focus in MediaLoep [10]. Focusing on multimedia and
other metadata, Reference [20] (more later) also has interoperability as a central task, along with
contributions such as References [2, 24, 53, 57].
Summary: Our review shows that the research on semantic knowledge graphs for the news
support a broad variety of tasks, such as semantic annotation, enrichment, content retrieval and
provision, event detection, relation and sub-graph extraction, KG updating, ontology development,
fake-news detection and fact checking, content generation, and prediction. The past few years have
seen a rapidly growing interest in KGs for fake-news identification. Support for factual journal-
ism is a related area that is growing. Automatic news detection is another emerging area that is
becoming increasingly important.

3.5 Input Data

As shown in Figure 3(a), the proposed approaches rely on a variety of sources and types of primary
input data. Note that this section discusses the data used as input by the solutions proposed or
discussed in each main paper, and not the data used for evaluation.
News articles: The most common input data are textual news articles in digital form. For ex-
ample, Reference [47] reads template-based HTML pages and exploits semantic regularities in the
templates to automatically annotate HTML elements with semantic labels according to their DOM
paths. Online news articles are also used as examples and for evaluation.
RSS and other news feeds: Other main papers take their inputs via RSS feeds or other news
feeds. The Ontology-based Personalised Web-Feed Platform (OPWFP) [28] inputs RSS news
streams and uses an ontology to provide more precisely customised web feeds. User profiles
are expressed using the semantic Composite Capability/Preference Profiles (CC/PP)A115 and
FOAFA24 vocabularies along with a domain ontology. The three vocabularies and ontologies are
used in combination to select appropriate search topics for the RSS search engine.
Social media and the Web: Several main papers use social media and other web resources as input,
such as Twitter,A110 Wikinews,A48 Wikipedia,A49 and regular HTML-based web sites. To support
personalised news recommendation and dissemination, the extension of VRT’s news workflow
mentioned earlier [44] uses OpenIDA41 and OAuthA9 for identification and authentication. In this

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:16 A. L. Opdahl et al.

way, the system can compile user profiles based on data from multiple social-media accounts, us-
ing ontologies such as FOAF and SIOCA23 to interoperate user data. Focusing on geo-hashtagged
tweets, Location Tagging News Feed (LTNF) [8] is a semantics-based system that extracts geo-
graphical hashtags from social media and uses a geographical domain ontology to establish re-
lations between the hashtags and the messages they occur in. Wikipedia is also used as a direct
source of input in a few papers [1, 36].
Multimedia news: Several papers use multimedia data as input. Reference [31] analyses news
texts in combination with associated images to suggest human-level image captions. To extend
the lifetime of TV news, the AGV pipeline [13] makes news videos from the RAI archives available
for geography education.
News metadata: Focusing on multimedia metadata, Reference [20] inputs metadata embedded
in formats such as MPEG-7 for content description and MPEG-21 for delivery and consumption.
The approach uses semantic mappings from XML Schema to OWL and from XML to RDF to integ-
rate administrative multimedia metadata in newspaper organisations. As already explained, Me-
diaLoep [10] also integrates descriptive multimedia news metadata from news production systems
semantically.
Knowledge graphs: Many papers use existing knowledge graphs as inputs. The number has risen
in the past few years due to the appearance of deep-NN architectures that infuse triples from open
KGs to enhance learning from news texts. Indeed, almost all the recent deep learning papers exploit
open KGs in this way, e.g., References [31, 40, 42, 66, 70, 80].
User histories: A smaller group of deep-NN papers inputs user histories, for example, in the form
of click logs, to train recommenders [19, 66, 70, 73].
Summary: Our review shows that the research on semantic knowledge graphs for the news
exploits a broad range of input sources. Textual news articles in digital form is the most important
source. Other frequently used types of input data are RSS and other news feeds, social media and
the Web, multimedia news, news metadata, knowledge graphs, and user histories. Multimedia,
including TV news, were popular in first years of the study period and have seen a rebound in
the deep-learning era. RSS and other news feeds were popular for many years, but have recently
been overtaken by social media, including Twitter. In recent years, KGs are being used increasingly
often to infuse world knowledge into deep NNs for news analysis. User histories have also been
used in recent recommendation papers.

3.6 News Life Cycle

The main papers also target different phases of the news life cycle, as shown in Figure 3(b). The
largest group of papers focuses on organising and managing already published news. For example,
Neptuno [7] extends the life of published news by annotating reports with keywords and IPTC
codes, thereby relating past news reports to current ones that share the same keywords or code.
It thus re-contextualises old news in light of more recent events. The MediaLoep data model [10]
supports managing information generated by news production and publishing processes. AGV [13]
makes archival news videos available for geography education.
Focus in recent years has shifted from focusing on already published news to also targeting
earlier phases of the news life cycle. As already mentioned, the Pundit algorithm [56] predicts
likely future news events based on short textual descriptions of current events. A small group
of mostly Twitter-based papers deals with detecting emerging news, or potentially newsworthy
events or situations that are not yet reported as news but that may be circulating in social media or
elsewhere. For example, Tweet2News [3] identifies emerging news from documentary (or headline-
like) tweets and lifts them into RDF graphs, which are then enriched with triples from the LOD
cloud and arranged into storylines to generate news reports in real time.

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:17

Focusing on breaking news, the Semantics-based Pipeline for Economic Event Detection
(SPEED) [24] uses a domain ontology to detect and annotate economic events. The approach
combines ontology-based word and event-phrase gazetteers; a word-phrase look-up component;
a word-sense disambiguator; and an event detector that recognises event-patterns described in a
domain ontology. The Evolutionary Event Ontology Knowledge (EEOK) [45] ontology presen-
ted earlier represents the typical evolution of developing news stories as patterns. It can thereby
be used to predict the most likely next events in a developing story and to train dedicated detectors
for different event types and phases (such as “investigation,” “arrest,” “court hearing”) in a complex
storyline (“fire outbreak”). RDFLiveNews [21] also follows developing news by combining statist-
ical and other machine-learning techniques to represent news events as knowledge graphs in real
time by extracting RDF triples from RSS data streams.
Summary: Our review shows that all the different phases of the news-life cycle are covered by
the research, from predicting future news, through detecting and monitoring emerging, breaking,
and developing news, to managing and exploiting already published news. Many main papers
attempt to cover several of these life-cycle phases.

3.7 Semantic Techniques and Tools

The main papers use a broad variety of semantic techniques and tools. For the purpose of this
review, we separate them into exchange formats, ontologies and vocabularies, information resources,
and processing and storage techniques.
Semantic exchange formats: By semantic exchange formats, we mean standards for exchanging
and storing semantic data. As shown in Figure 4(a), RDF, OWL, and SPARQL are most common.
More than half of the papers use RDF to manage information. The earliest example is Neptuno [7],
which uses RDF to represent the IPTC’s hierarchical subject reference system.A70 More than a
third of the main papers use OWL for ontology representation. For example, the MediaLoep data
model [10] is represented in OWL (using the SKOS vocabulary), and its concepts are linked to
standard knowledge bases such as DBpedia [85] and GeoNames.A51 And we have already men-
tioned the NEWS Ontology [17], which is represented in OWL-DL,A118 the description logic subset
of OWL. SPARQL is also common. It is central in the Hermes project [4] and in the News Articles
Platform [53]. RDFSA122 is also widely used, including in the NEWS [15] project.
Ontologies and vocabularies: By ontologies and vocabularies, we mean formal terminologies for
semantic information exchange. As shown in Figure 4(b), Dublin Core (DC) and Friend of a
Friend (FOAF) are the most used general vocabularies, starting already with KIM [37], whose on-
tology is designed to be aligned with them both. The NEWS project [15] also uses DC, whereas
FOAF plays a prominent role in a few approaches that deal with personalisation, in particular in
a social context [28, 44]. Another much-used ontology is the Simple Knowledge Organization
System (SKOS). It is used by the NEWS Ontology [17] to align and interoperate concepts from
different annotation standards, including the IPTC News Codes.A68 It is also used for personal-
ised multimedia recommendation in Reference [26] and for integrating news-production metadata
in Reference [10]. The OWL-representation of IPTC’s News Codes in Reference [71] links to Dub-
lin Core and SKOS concepts to increase precision and facilitate content enrichment. The Simple
Event Model (SEM)A111 and OWL TimeA119 are used in the NewsReader [72] and News Angler
projects [46]. SUMO/MILO A97 is used in the NEWS project [15]. SUMO and ESO A99 are used in
NewsReader [59, 72]. Other general ontologies include schema.org, used to contextualise the Claim-
sKG [69] and KIM’s PROTON ontologyA1 [37]. The Provenance Data Model (PROV-DM) is used
to discover high-level provenance using semantic similarity in [9]. Although several other papers
mention provenance, too, they do not explicitly refer to or use PROV-DM, nor its OWL formulation,
PROV-O.A120 However, the NewsReader project [72] uses the Grounded Representation and

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:18 A. L. Opdahl et al.

Fig. 4. The most frequently used semantic (a) exchange formats and (b) vocabularies and ontologies.

Source Perspective (GRaSP) framework, which has at least been designed to be compatible with
PROV-DM.
On the news side, the rNews vocabularyA69 is used for semantic mark-up of web news resources
in several papers. Whereas most of the papers in this review rely on the older versions of rNews, the
ASRAEL project [60] uses its newer schema.org-based rNews vocabulary. The Internationaliza-
tion Tag Set (ITS)A116 is also used in a few papers, for example, to unify claims in ClaimsKG [69],
The IPTC’s General Architecture Framework (GAF)A66 is used in NewsReader [59, 72].
On the natural-language side, several proposals [21, 69, 72] use the RDF/OWL-based NLP Inter-
chance Format (NIF)A87 to exchange semantic data between NLP components. In addition, more
than a third of the papers propose their own domain ontologies.
Semantic information resources: By semantic information resources, we mean open knowledge
graphs, or openly available semantic datasets expressed as triples. As shown in Figure 5(a), se-
mantic encyclopedias are most frequently used. More than a quarter of the main papers some-
how exploit DBpedia. It is, for example, used by NewsReader [59, 72] for semantic linking and
enrichment. Wikidata is an alternative that is used in several recent approaches. It is used by
ASRAEL [60] and VLX-Stories [14] to support semantic labelling, enrichment, and search, and it
used to detect fake news in Reference [5]. There is also increasing uptake of Google’s KG, which
is used by VLX-Stories [14] to detect emerging entities, in Reference [61] to separate emerging
from already-known entities, and by AGV [13] to provide additional information about entities
extracted from educational TV programs. Although it has been seeded into Google’s knowledge
graphA104 and is no longer maintained, Freebase is still being used for external linking in K-Pop [36],
for content-based recommendation in Reference [33], for evaluation of TAMURE [78], and for en-
riching government data in Reference [62] (more later). GeoNames is used as the reference graph
for geographical information in many papers, such as References [10, 44, 46, 62, 63, 71, 72]. With
the availability of large one-stop KGs like these, fewer papers than before rely on the LOD cloud
in general. An exception is Reference [26], which exploits the LOD cloud to identify news stories
that match users’ interests.
Beyond general semantic encyclopedias and other LOD resources, YAGO2 A58 and its integra-
tion of WordNet event classes is used in Reference [38] to classify named news events. The ini-
tial version of YAGO is used by Pundit [56] to build a world entity graph for mining causal
relationship between news events, and in Reference [74] to infuse world knowledge into a
Knowledge-driven Multimodal Graph Convolutional Network (KMGCN) for fake news
detection. Common-sense knowledge from the Cyc project [112] is used, too, for example, to

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:19

Fig. 5. The most frequently used semantic (a) information resources and (b) processing techniques.

augment reasoning over semantic representations mined from financial news texts [51] and to
predict future events [56]. PolarisX [77] uses ConceptNet 5.5 A106,A107 as a development case and
for evaluating its approach to automatically expand knowledge graphs with new news events.
ConceptNet is also used by Pundit [56]. Several of the general semantic information resources,
such as DBpedia, ConceptNet, Cyc, Wikidata, and YAGO, come with their own resource-specific
ontologies and vocabularies in addition to the ones mentioned in the previous section.
On the natural language side, WordNet [98, 117] is not natively semantic, but it is used in a
third of the main papers—more than any of the natively semantic resources—including Hermes [4],
NewsReader [59, 72], and SPEED [24]—although only a single paper [58] explicitly mentions Word-
Net’s RDF version.A125
Semantic processing techniques: By semantic processing technique, we mean programming
techniques and tools used to create and exploit semantic information resources. As shown in
Figure 5(b), entity linking [82] is the most frequently used technique by far. The most used en-
tity linkers are DBpedia Spotlight, Thomson-Reuters’ OpenCalais,A109 and TagMe. Beyond entity
linking, seven papers employ logical reasoning. Description logicA82 and OWL-DL is used for
trust-based resolution of inconsistent KBs in Reference [22] and for managing the NEWS Onto-
logy [17]. Other papers mention general ontology-enabled reasoning without OWL-DL. For ex-
ample, PWFF [28] and Reference [51], which uses Cyc to answer questions about business news.
Rule-based inference is also used, e.g., in References [6, 15, 20, 35, 57]. The most common program-
ming API for semantic data processing is Apache’s Java-based Jena framework,A44 used in 12 main
papers. Only 4 papers mention Python’s RDFlib,A11 most of them from recent years. ProtégéA112
is used in 4 papers, for example, for ontology development in Neptuno [7] and in the NEWS pro-
ject [15].
Semantic storage techniques: Although almost all the main papers mention ontologies or know-
ledge graphs, few of them discuss storage and none of them focus primarily on the storage side.
The two most frequently used triple stores are RDF4JA39 (formerly Sesame) used by four papers
and OpenLink VirtuosoA105 also used by four papers. AllegroGraphA65 is employed in two pa-
pers [44, 49]. Used by NewsReader [59, 72], the KnowledgeStoreA28 is designed to store large col-
lections of documents and link them to RDF triples that are extracted from the documents or
collected from the LOD cloud. It uses a big-data ready file system (Hadoop Distributed File Sys-
tem, HDFSA103 ) and databases (Apache HBaseA43 and VirtuosoA105 ) to store unstructured (e.g.,
news articles) and structured information (e.g., RDF triples) together.

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:20 A. L. Opdahl et al.

Summary: Our review demonstrates that the research on KG for news exploits a broad variety
of available semantic resources, techniques, and tools. The research on KGs for news differs from
the mainstream research on KGs mainly in its stronger focus on language (e.g., the ITS and NIF
vocabularies), on events (e.g., the SEM ontology), and, of course, on news (the rNews vocabulary).
The border between semantic and non-semantic computing techniques is not always sharp. For
example, although WordNet is not natively semantic, it is available as RDF and is used as a semantic
information resource in many proposals. A recent trend is that Wikidata is becoming more popular
compared to DBpedia.

3.8 Other Techniques and Tools

Most main papers use semantic knowledge graphs in combination with other techniques and tools.
Similar to the previous section, we separate them into exchange formats, information resources, and
processing and storage techniques. The online Addendum (Section B.1) presents a detailed review,
which shows that the research on semantic knowledge graphs for the news is technologically
diverse. We find examples of research that exploit most of the popular news-related standards
and most of the popular techniques for NLP, machine learning, deep learning, and computing in
general.
On the news side, the IPTC family of standards and resourcesA72,A71,A66 is central. On the
NLP side, entity extraction, NL pre-processing, co-reference resolution, morphological analysis,
and semantic-role labelling are common, whereas GATE,A92 Lucene,A45 spaCy,A35 JAPE,A93 and
StanfordNERA57 are the most used tools.
On the ML side, the past decade has seen more and more proposals that exploit machine-
learning techniques, as illustrated by three early examples from 2012: Reference [9] uses greedy
clustering to automatically detect provenance relations between news articles. The Hermes frame-
work [29] uses a pattern-language and rule-based approach to learn ontology instances and event
relations from text, combining lexico-semantic patterns with semantic information. It is used to
analyse financial and political news articles, splitting its corpus of news articles into a training
and a test set. Pundit [56] mines text patterns from news headlines to predict potential future
events based on textual descriptions of current events. It uses machine learning to automatic-
ally induce a causality function based on examples of causality pairs mined from a large collec-
tion of archival news headlines. Whereas these early approaches rely on hand-crafted rules and
dedicated learning algorithms, more recent proposals use standard machine-learning techniques
for word, graph, and entity embeddings, such as TransE [89], TransR [113], TransD [110], and
word2vec [116].
On the DL side, there has been a sharp rise since 2019 in deep learning [102] approaches. Po-
larisX [77] uses pre-trained multilingual BERT model to detect new relations, with the aim of
updating its underlying knowledge graph in real time. TAMURE [78] uses tensor factorisation
implemented in TensorFlowA13 to learn joint embedding representations of entities and relation
types. Focusing on click-through rate (CTR) prediction in online news sites, DKN [73] uses a
Convolutional Neural Network [102] with separate channels for words and entities and an atten-
tion module to dynamically aggregate user histories. Reference [19] proposes a deep neural net-
work model that employs multiple self-attention modules for words, entities, and users for news
recommendation. Reference [52] proposes the B-TransE model to detect fake news based on con-
tent. The most used deep learning techniques and tools are CNN [102], GRU [102], GCN [91, 103],
LSTM [102], BERT [96], and attention [135].
The focus on news standards is strongest in the first part of the study period, up to around 2014,
when many approaches incorporate existing news standards into the emerging LOD cloud [87].

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:21

Fig. 6. The most frequently targeted (a) news domains and (b) languages.

The second part, from around 2015, sees a shift towards machine learning approaches [119], first
focusing on NLP and embedding techniques and, since around 2019, on deep learning [102].

3.9 News Domain

As shown in Figure 6(a), most of the main papers do not focus on a particular news domain, ex-
cept as examples or for evaluation. Among the domain-specific papers, economy/finance is most
common. For example, Reference [43] presents a semantic search engine for financial news that
uses an automatically populated knowledge graph that is kept up to date with semantically annot-
ated financial news items, and we have already mentioned the SPEED pipeline for economic event
detection and annotation in real time [24].
Politics is the theme of over 900,000 French tweets collected to trace propagation of knowledge,
misinformation, and hearsay [12]. Reference [62] uses named entity linking to contextualise open
government data, making them available in online news portals alongside related news items that
match each user’s interests. In the sports news domain, Reference [50] proposes a recommender
system based on BKSport [49] that combines semantic and content-based similarity measures to
suggest relevant news items. Other domains targeted by multiple papers include science [13, 57],
business [41, 51], health [13, 23], and the stock market [4, 41].
Targeting entertainment news, K-Pop [36] builds on an entertainer ontology to compile a se-
mantic knowledge graph that represents the profiles and activities of Korean pop artists. The
artists’ profiles in the graph are based on information from WikipediaA49 and enriched with con-
tent from DBpedia [85], Freebase,A2 LinkedMDB,A6 and MusicBrainz.A40 They are also linked to
other sources that represent not only the artist, but also their activities, business, albums, and
schedules. The graph and ontology are used in the Gnosis app to enhance K-Pop entertainment
news with information about artists retrieved from the knowledge graph.
WebLyzard [63] identifies topics and entities in news about the environment and uses visual-
isations to present lexical, geo-spatial, and other contextual information to gain overview of per-
ceptions of and reactions to environmental threats and options. AGV [13] targets education, in
particular in science and technology. Other domains include medicine [23], crime [67], and earth
science [57].
Summary: Our review suggests that semantic knowledge graphs and related semantic tech-
niques are useful in a broad range of news domains. Most investigated so far are economy and
finance. There is little domain-specificity in the research so far: Most architectures and techniques
proposed for one news domain appear readily transferable to others. The higher interest in the

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:22 A. L. Opdahl et al.

Table 2. The Five Most Frequently Cited Main Papers (Recency Weighted)
Title Year Ref # citations Citation # main paper
weight citations
DKN: Deep knowledge-aware network for news recommendation 2018 [73] 413 33.15 4
Semantic annotation, indexing, and retrieval 2004 [37] 523 16.34 1
Learning causality for news events prediction 2012 [56] 199 9.64 2
Building event-centric knowledge graphs from news 2016 [59] 111 7.35 2
Content-based fake news detection using knowledge graphs 2018 [52] 72 5.78 1

financial and business domains may result from economic opportunities combined with the avail-
ability of both quantitative and qualitative data streams in real time.

3.10 Language
As shown in Figure 6(b), the most frequently covered languages beside English are Italian and
Spanish, but neither is supported by more than 10 papers. Support for French and German in the
main papers appear only in combination with English. Many papers deal with a combination of
several languages, such as English, Italian, and Spanish in the NEWS project [15], and a few recent
approaches explicitly aim to be multi-lingual (or language-agnostic). For example, NewsReader [72]
mentions Dutch, Italian, and Spanish in addition to English, whereas PolarisX [77] aims to cover
Chinese, Japanese, and Korean.
Summary: Our review suggests that English is the best supported language by far but, of course,
this may be because we use English language as an inclusion criterion. Additional papers address-
ing other major languages, such as Chinese, French, German, Hindi, and Spanish, may instead be
written and published in their own languages. The other most frequently supported languages
are Spanish, Italian, French, Chinese, Dutch, German, and Japanese, with many of the Chinese
and Japanese papers published in recent years. Many approaches also support more than one lan-
guage, exploiting the inherent language-neutrality of ontologies and knowledge graphs. There is
a growing interest in offering multi-language and language-agnostic solutions.

3.11 Important Papers

Our main papers reference 1,842 earlier papers and are themselves cited 2,381 times according
to Semantic Scholar.A36 Table 2 shows that the most cited of our main papers is the one about
KIM [37] from 2004, with the much more recent DKN paper [73] from 2018 second. The paper about
Pundit [56] from 2012 is also frequently cited. To account for recency, Table 2 is therefore ordered
by citation numbers that are weighted against the expected number of citations of a main paper
from the same year.3 Just outside the top five, References [21, 24, 38, 69, 72] are also frequently
cited.4
Table 3 shows the papers that are referenced most frequently by our main papers.5 Among
the outgoing citations, seminal papers on the Semantic Web [86] and on WordNet [98] are most
frequently cited. Also much cited are the central papers on GATE, TransE, and word2vec. Just
outside the top five, other frequently referenced papers are References [85, 88, 113, 132, 136], con-
firming the importance of LOD resources and embedding models for the research on semantic

3 To weight the citation counts, the three most frequently cited papers (i.e., [37, 56, 73]) are removed as outliers. Average

citation counts are calculated for each year for the remaining main papers. A support-vector regression (SVR) model is
trained using scikit-learn [119] with a radial-basis function (RBF) kernel, C = 1,000, and γ = 0.001. Finally, the citation
count for each paper is divided by the count predicted for a paper from that year.
4 The online Addendum (Table 11) presents an extended top-15 list.
5 We do not report weighted reference counts, because more recent papers are much more frequently cited in our dataset,

giving unreasonably high relative weight to older papers even when they are referenced only once or a few times.

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:23

Table 3. The Five Papers Most Frequently Referenced by Our Main Papers
Title Year Ref # main paper refs
The semantic web 2001 [86] 15
WordNet: An electronic lexical database 2000 [98] 11
Translating embeddings for modeling multi-relational data 2013 [89] 8
GATE, a general architecture for text engineering 1997 [95] 7
Distributed representations of words and phrases and their compositionality 2013 [116] 7

Table 4. (a) Authors with Three Main Papers or More and (b) Projects with Multiple Papers
Author Main papers # main Project # papers # citations # main
papers citations
F. Frasincar [4, 24, 25, 29, 32, 58, 64] 7 Hermes 7 188 2
F. Hogenboom [24, 25, 29, 58, 64] 5 NewsReader 2 171 2
D. Deursen, E. Mannens, R. Walle [9, 10, 44] 3 “Wuhan” 2 73 0
N. García, L. Sánchez [15–17] 3 NEWS 3 73 4
“MediaLoep” 3 45 0
“Chicago” 2 8 0
BKSport 2 8 0
(a) (b)

Table 5. Groups of Authors Connected by Chains of Two or More Co-authored Papers

Authors Refs Project
J. Borsje, F. Frasincar, F. Hogenboom, L. Levering, K. Schouten [4, 24, 25, 29, 32, 58, 64] Hermes
S. Coppens, D. Deursen, E. Mannens, R. Sutter, R. Walle [9, 10, 44] “MediaLoep”
J. Arias-Fisteus, A. Bernardi, N. García, L. Sánchez, J. Toro [15–17] NEWS
N. Li, C. Li, J. Pan [42, 52] “Wuhan”
Y. Chang, C. Lu, J. Zhang [78, 79] “Chicago”
T. Cao, Q. Nguyen [49, 50] BKSport
I. Aldabe, M. Erp, A. Fokkens, G. Rigau, M. Rospocher, P. Vossen [59, 72] NewsReader

KGs for news.6 Closely related to our main papers, another paper on KIM [128] is cited six times,
and Reference [109], a precursor to the SemNews paper [30], is also cited several times.
Summary: No paper yet stands out as seminal for the research area. With the exception of the
KIM project, none of the main papers or projects are frequently cited by other main papers, sug-
gesting that research on semantic KGs has not yet matured into a clearly defined research area
that is recognised by the larger research community.

3.12 Frequent Authors and Projects

Table 4(a) shows the most frequent main-paper authors, along with their most centrally related
projects. Table 5 also shows co-authorship cliques, defined by chains of at least two co-authored
papers. The table shows that repeated co-authorship among the frequent authors occurs exclus-
ively within a small number of research projects (or persistent collaborations), such as NEWS [15],
Hermes [4], and NewsReader [72].7
The seven cliques cover all the repeated collaborations, we have found. Table 4(b) also shows
the cumulative citation counts for each project or collaboration. Hermes and NewsReader are
the most frequently cited projects, but there are very few citations to these and to the other pro-
jects/collaborations from other main papers. Indeed, none of the main papers from the seven listed
projects and collaborations are citing one another (although, of course, such cross-references may

6 Theonline Addendum (Table 12) again presents an extended top-15 list.

7 Table5 also introduces informal names such as “MediaLoep” and “Wuhan” for persistent collaborations that are not
centred around a single named project.

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:24 A. L. Opdahl et al.

Fig. 7. Timeline for the percentages of main papers from each year that match the sub-themes Semantic
Web, LOD, KGs, and deep learning.8

still exist between papers from the same projects that we have not included as main papers). Only
43 references in total are from one main paper to another (the online Addendum (Figure 10) presents
a citation graph).
Summary: The analysis underpins that the research on semantic KGs has not yet matured into
a distinct research area. The research is carried out mostly by independently working researchers
and groups, although the NewsReader project has involved several institutions located in different
countries. There is so far little collaboration and accumulation of knowledge in the area, although
the early KIM [37] proposal has been used in later research.

3.13 Evolution over Time

The research on semantic knowledge graphs for news can be divided into four eras that broadly
follow the evolution of knowledge graphs and related technologies in general: the Semantic Web
(–2009), Linked Open Data (LOD, 2010–2014), knowledge graphs (KGs, 2015–2018), and deep
learning (DL, 2019–) eras. Figure 7 presents corresponding timelines that show the percentage
of main papers from each year that match each theme. To underpin the separation into four eras
further, the online Addendum (Section B.2) presents additional timelines that show typical sub-
themes from each era.
The first era (until around 2009) is inspired by the Semantic-Web idea and early ontology work.
Almost all the main papers from this era mention the Semantic Web or Semantic-Web technologies
prominently in their introductions. They combine basic natural-language processing with central
Semantic-Web ideas such as semantic annotation, domain ontologies, and semantic search applied
to the news domain. Many of the papers bring existing news and multimedia publishing stand-
ards into the Semantic-Web world, and the IPTC Media TopicsA67 are therefore important. Central
semantic techniques are RDF, RDFS, OWL, and SPARQL, and important tasks are archiving and
browsing. There is also an early interest in multimedia. Figure 8(a) shows a word cloud of the most
prominent sub-themes for papers published during this era.
The main papers in second era (2010–2014, but starting with Reference [71] already in 2008)
trails the emergence of the LOD cloud [87], which many of the papers use to motivate their contri-
butions. Contextualisation and other types of semantic enrichment of news texts is central, aiming
to support more precise search and recommendation. Although some papers use Wikipedia and
DBpedia for enrichment, the most used information resource is WordNet. To link news texts pre-
cisely to existing semantic resources, more advanced pre-processing of news texts is used along

8 The timeline depicts three-year averages.

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:25

Fig. 8. Word clouds for (a) the Semantic-Web era (until around 2009), (b) the Linked Open Data (LOD) era
(around 2010–2014), (c) the knowledge-graph era (around 2015–2018), and (d) the deep-learning era (from
around 2019).

with techniques such as morphological analysis and vector spaces. GATE is a much-used NLP tool
in this era, as is OpenCalais for entity linking and Jena for managing RDF data.
The third era (2015–2018), reflects Google’s adoption of the term “Knowledge Graphs” in
2012A104 and the growing importance of machine learning [119]. One of the first main papers
to mention knowledge graphs is Reference [2] already in 2013, but most of the main papers are
published starting in 2015. The research increasingly considers knowledge graphs independently
of semantic standards such as RDF and OWL, and uses machine learning and related techniques
to analyse news texts more deeply, for example, extracting events and facts (relations). DBpedia
and entity linking become more frequently used, along with word and graph embeddings. On the
NLP side, co-reference resolution and dependency parsing become more important, along with
StanfordNER.
Since around 2019, a fourth and final era starts to emerge. Typical approaches analyse news
articles using deep neural network (NN) architectures that combine text- and graph-embedding
approaches and that infuse triples from open KGs into graph representations of news texts. Central
emerging tasks are fact checking, fake-news detection, and click-through rate (CTR) prediction.
Deep-learning techniques such as CNN, LSTM, and attention become important, and spaCy is used
for NLP. On the back of deep image-analysis techniques, multimedia data also makes a return.
Because the boundary between this and the KG era is not sharp, the word cloud in Figure 8(d) has
many similarities to Figure 8(c).

4 DISCUSSION
Based on the analysis, this section will discuss each main theme in our analysis framework (Table 1).
We will then answer the four research questions posed in the Introduction and discuss the limita-
tions of our article.

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:26 A. L. Opdahl et al.

Table 6. Conceptual Framework

Technical result type: pipeline/prototype (58), ontology (18), system architecture (16), algorithm (15), NN architecture (9), KG
(7), production system (4)
Empirical result type: experiment (58), examples (17), ablation study (7), PoC demo (6), performance evaluation (5), case
study (4), parameter study (4), explainability study (4), user study (4), use case (3), industrial testing (3)
Intended users: news users (45), journalists (32), KB maintainers (10), newsrooms (9), fake news detectors (8),
knowledge workers (6), archivists (5), fact checkers (3), news agencies (3)
Task: semantic annotation (28), retrieval (22), event detection (20), provision (19), enrichment (18), relation
extraction (9), KG updating (9), ontology development (8), KG population (7), fake news detection (7),
personalisation (6), archiving (6), sub-graph extraction (5), prediction (5), content generation (5),
visualisation (4), similarity detection (3), fact checking (3), integration/interoperability (3)
Input data: news articles (59), news feeds (23), RSS feeds (17), KG (11), social media (10), multimedia (8), Twitter
(6), TV news (4), user histories (4), news metadata (3)
Life-cycle phase: published news (58), developing news (13), breaking news (7), emerging news (3), future news (1)
Semantic techniques: Semantic exchange formats: RDF (43), OWL (28), SPARQL (25), KG (18), RDFS (12) • Semantic
ontologies and vocabularies: FOAF (6), DC (6), SKOS (5), rNews (4), NIF (3), schema.org (3), SEM (3),
PROTON (2), ITS (2), SUMO/MILO (2), OWL Time (2), ESO (2), GAF (2) • Semantic information
resources: domain ontology (31), DBpedia (23), LOD (14), Freebase (9), Wikidata (9), GeoNames (7),
Google KG (3), YAGO (3), OpenCyc (2), ConceptNet (2) • Semantic processing techniques: entity linking
(32), Jena (12), reasoning (7), inference (6), DBpedia Spotlight (5), OpenCalais (4), description logic (4),
RDFLib (4), Protege (4), TagMe (3) • Semantic storage techniques: Virtuoso (4), RDF4J/Sesame (4),
AllegroGraph (2), KnowledgeStore (2)
Other techniques: Other exchange formats (general): XML (13), HTML (10), JSON (5), MPEG-7 (4), CSS (3), XML Schema (2)
• Other exchange formats (news): NewsML (6), NITF (2), NAF (2) • Other resources (general):
Wikipedia (14), Twitter (4), Yahoo! Finance (2), ISO country codes (2), CIA WorldFact Book (2), NASDAQ
company codes (2) • Other resources (news): IPTC Media Topics (7), IPTC NewsCodes (2) • Other
resources (language): WordNet (22), VerbNet (4), Penn Treebank (2), Predicate Matrix (2), PropBank (2),
FrameNet (2) • Other processing techniques (language): entity extraction (36), NL pre-processing (33),
coreference resolution (11), GATE (10), Lucene (7), spaCy (7), JAPE (6), morphological analysis (6),
StanfordNER (5), SRL (5), WSD (4), relation extraction (4), dependency parsing (4), sentiment analysis (4),
StanfordNLP (4) • Other processing techniques (machine learning/deep learning): word embeddings
(13), graph embeddings (8), CNN (6), TransE (5), GRU (4), hierarchical clustering (3), GCN (3), word2vec
(3), attention (3), TransR (3), LSTM (3), BERT (3), entity embeddings (3) • Other storage techniques:
MongoDB (2), MySQL (2), relational DB (2), Heuristic and Deductive Database (2)
News domain: economy/finance (7), politics (3), science (2), health (2), sports (2), business (2), stock market (2), earth
science (1), technology (1), crime (1), evolutionary events (1), medicine (1), entertainment (1), climate
change (1), environment (1)
Language: English (44), multiple languages (14), Spanish (9), Italian (8), French (6), Chinese (5), Dutch (4), German
(3), Japanese (3)

4.1 Conceptual Framework

Table 6 shows the conceptual framework that results from populating our analysis framework in
Table 1 with the most frequently used sub-themes from the analysis. It is organised in a hierarchy of
depth up to 4 (e.g., Other techniques: → Other resources → language → WordNet). The framework
shows which areas and aspects of semantic knowledge graphs for news that have so far been most
explored in the literature. It can be used both as an overview of the research area, as grounds for
further theory building, and as a guide for further research.
The earliest versions of our framework also contained geographical region as a top-level theme,
alongside news domain and language, but very few of our main papers were specific to a region,
and never exclusively so. For example, although the contextualisation of open government data
in Reference [62] focuses on Colombian politics, the proposed solution is straightforwardly adapt-
able to other regions.

4.2 Implications for Practice

For each main theme, this section suggests implications for practice, before the next section pro-
poses paths for further research.
Technical result types: There are already many tools and techniques available that are suffi-
ciently developed to be tested in industrial workflows. Commercial tools such as VLX-Stories [14]

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:27

and ViewerProA102 are also starting to emerge. But most research proposals are either research
pipelines/prototypes or standalone components that require considerable effort to integrate into
existing workflows before they can become productive. Pilot projects that match high-benefit tasks
with low-risk technologies and tools are therefore essential to successfully introduce semantic KGs
in newsrooms.
Empirical result types: Although there are examples of tools and techniques that have been de-
ployed in real news production workflows, they are the exception rather than the rule. This poses
a double challenge for newsrooms that want to use KGs for news: It is usually not known how ro-
bust the proposed techniques and tools are in practice, and it is usually not known how well they
fit actual industrial needs. Introducing KGs into newsrooms must therefore focus on continuous
evaluation both of the technology itself and of its consequences, opening possibilities for collab-
oration between industry (which wants its projects evaluated) and researchers (who want access
to industrial cases and data).
Intended users: The most mature solutions support journalists through tools and techniques
for searching, archiving, and content recommendation. The general news user is supported by
proposals for news recommendation and to some extent searching.
Tasks: The most mature research proposals target long-researched tasks such as semantic an-
notation, searching, and recommendation, both for content retrieval (pull) and provision (push).
In particular, annotation of news texts with links to mentioned entities and concepts is already
used in practice and will become even more useful as the underlying language models continue to
improve. Semantic searching and browsing are also well-understood areas. Semantic enrichment
with information from open KGs and other sources is a maturing area that builds on a long line
of research, but suffers from the danger of creating information overload. Rising areas that are
becoming available for pilot projects are automatic news detection and automatic provision of
background information.
Input data: The most mature tools and techniques are text-based. When multimedia is suppor-
ted, it is often done indirectly by first converting speech to text or by using image captions only.
Newer approaches that exploit native audio and image analysis techniques in combination with
semantic KGs may soon become ready for industrial trials. Many newsrooms already have exper-
ience with robots [118] that exploit input data from sensors, the Internet of Things (IoT), and
open APIs [84]. This creates opportunities to explore new uses of semantic KGs that augment exist-
ing robot-journalism tools and techniques. Much of the research that exploits social media is based
on Twitter. This poses a challenge, because Twitter use is dwindling in some parts of the world,
sometimes with traffic moving to more closed platforms, such as Instagram, Snapchat, Telegram,
TikTok, WhatsApp, and so on. In response, news organisations could attempt to host more social
reader interactions inside their own distribution platforms, where they retain access to the user-
generated content. Semantic KGs offer opportunities through their support for personalisation,
recommendation, and networking.
News life cycle: Low-risk starting points for industrial trials are the mature research areas based
on already-published news, such as archive management, recommendation, and semantically en-
riched search. Automated detection of emerging news events and live monitoring of breaking news
situations are higher-risk areas that also offer high potential rewards.
Semantic techniques: Because they tend to rely on standard semantic techniques, many of the
proposed techniques can be run in the cloud, for example, in Amazon’s Neptune-centric KG
ecosystemA17 and supported by other Amazon Web Services for NLP and ML/DL.A16 Cloud in-
frastructures give newsrooms a way to explore advanced computation- and storage-intensive KG-
based solutions without investing heavily upfront in new infrastructure.

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:28 A. L. Opdahl et al.

Other techniques: The demonstrated ability of KG-based approaches to work alongside a wide
variety of other computing techniques and tools suggests that newsrooms that want to exploit
semantic KGs should build on what they already have in place, using KG-based techniques to
augment existing services and capabilities. For example, KGs are well suited to integrate diverse
information sources through exchange standards such as RDF and SPARQL and ontologies ex-
pressed in RDFS and OWL. One possibility is therefore to introduce them in newsrooms as part of
ML and DL initiatives that need input data from multiple and diverse sources, whether internal or
external. Semantic analysis of natural language texts, audio, images, and video is rapidly becoming
available as increasingly powerful commodity services. KGs in newsrooms could be positioned to
enrich and exploit the outputs of such services, acting as a hub that can represent and integrate
the results of ML- and DL-driven analysis tools and prepare the data for journalists and others.
News domain: For newsrooms that want to exploit KGs, the most mature domains are business
and finance. For example, ViewerPro,A102 an industrial tool for ontology-based semantic analysis
and annotation of news texts, has been applied to gain effective access to relevant finance news.
The proposed tools and techniques are often transferable across domains and purposes. Good can-
didates for industrial uptake are domains that are characterised by data streams that are reliable
and high-quality, but insufficiently structured for currently available tools, e.g., for robot journal-
ism [118]. Using KG-techniques to expand the reach and capabilities of existing journalistic robots
may be a path to reap quick benefits from KGs on top of existing infrastructures.
Language: Given the focus on English in the research on semantic KG for the news and on NLP
in general, international news is a natural starting point for newsrooms in non-English speaking
countries that want to explore KG-based solutions. For newsrooms in English and other major-
language countries, KG-powered cross-lingual and language-agnostic services can be used to sim-
plify searching, accessing, and analysing minor-language resources, offering a low-effort/high-
reward path to introducing semantic KGs.

4.3 Implications for Research

Based on our analysis of main papers, this section proposes paths for further research.
Technical result types: More industrial-grade prototypes and platforms are needed in response
to the call for industrial testing. Much of the current research, such as the exploration of deep
learning and other AI areas for news purposes, is technology-driven and needs to be balanced by
investigations of the needs of journalists, newsrooms, news users, and other stakeholders.
Empirical result types: To better understand industrial needs, challenges, opportunities, and ex-
periences, empirical studies are called for, using the full battery of research approaches, includ-
ing case- and action-research, interview- and survey-based research, and ethnographic studies of
newsrooms. Research on semantic knowledge graphs for the news might benefit from the growing
and complementary body of literature on augmented, computational, and digital journalism (e.g.,
References [92, 97, 129, 134]), which focuses on the needs of newsrooms and journalists, but goes
less into detail about the facilitating technologies, whether semantic or not. Indeed, the research on
semantic KGs for the news hardly mentions the literature on augmented/digital/data journalism
which, vice versa, does not go into the specifics of KGs.
Most papers that propose new techniques or tools offer at least some empirical evaluation
of their own proposals. Experimental evaluations using gold-standard datasets and information-
retrieval measures are becoming increasingly common, but there is no convergence yet towards
particular gold-standard datasets and measures, which makes it hard to compare proposals and as-
sess overall progress. This is an important methodological challenge for further research. We also
find no papers that focus on evaluating tools or techniques proposed by others. Also, the papers

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:29

that develop pipelines and prototypes are seldom explicit about the design research method they
have followed.
Intended users: We found no papers discussing semantic knowledge graphs and related tech-
niques for citizen journalism, for example, investigating social semantic journalism as outlined
in Reference [105]. Local journalism [122, 133] is also not a current focus, and we found few
papers that explicitly mention newsrooms or consider the social and organisational sides of news
production and journalism. There is also no mentioning of robot journalism in the main papers.
Tasks: More research is needed in areas that are critical for representing news content on
a deeper level, beyond semantic annotation with named entities, concepts, and topics. Central
evolving areas are event detection, relation extraction, and KG updating, in particular identifica-
tion and semantic analysis of dark entities and relations.
There is little research on the quality of data behind semantic KGs for news. Aspects of semantic
data quality, such as privacy, provenance, ownership, and terms of use, need more attention. Few
research proposals target or undertake multimedia analysis natively (i.e., without going through
text) and specifically for news.
Input data: The research on social media tends to focus on short texts, which are hard to analyse,
because they provide less context and use abbreviations, neologisms, and hashtags [131]. More
context can be provided by integrating newer techniques that also analyse the audio, image, and
video content in social messages. Some research approaches harvest citizen-provided data from
social media, but there are no investigations of how to use semantic techniques and tools parti-
cipatively for citizen journalism [105]. There is little research on KGs for news that exploits data
from sensors and from the IoT in general [84], and there is little use of open web APIs outside
a few domains (such as business/finance). We have already mentioned the ensuing possibility of
combining semantic KGs with robot-journalism tools and techniques. GDELTA98 is another un-
tapped resource, although data quality and ownership is an issue. Research is needed on how its
data quality can be corroborated and improved. Also, the low-level events in GDELT data streams
need to be aggregated into news-level events.
News life cycle: Relatively little research targets detecting emerging news events, monitoring
breaking news situations, and following developing stories. Event detection and tracking as well
as detecting emerging entities and relations are important research challenges.
Semantic techniques: Most of the research uses existing news corpora or harvests news art-
icles on-demand. There is less focus on building and curating journalistic knowledge graphs over
time. Due to the high volume, velocity, and variety of news-related information, semantic news
KGs are a potential driver and test bed for real-time and big-data semantic KGs. More research
is therefore needed on combining KGs with state-of-the-art techniques for real-time processing
and big data. Yet, none of the main papers have primary focus on the design of semantic data ar-
chitectures/infrastructures for newsrooms, for example, using big-data infrastructures, data lakes,
web-service orchestrations, and so on. The most big-data-ready research proposal is NewsReader,
through its connection with the big-data ready KnowledgeStoreA28 repository. The News Hunter
platform developed in the News Angler project [46] is also built on top of a big-data ready infra-
structure [100]. In addition to supporting processing of big data in real time, these architectures and
infrastructures must be forward-engineered to accommodate the increasing availability of high-
quality, high-performance commodity cloud-services for NLP, ML, and DL that can be exploited
by news organisations.
Other techniques: On the research side, few approaches to semantic KGs for news exploit recent
advances in image understanding and speech recognition. There is a potential for cross-modal solu-
tions that increase precision and recall by combining analyses of text, audio, images and, eventually,
video. These solutions need to be integrated with semantic KGs, and their application should focus

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:30 A. L. Opdahl et al.

on areas where KGs bring additional benefits, such as infusing world and common-sense know-
ledge into existing analyses. Also, few approaches so far exploit big-data and real-time computing.
Although some proposals express real-time ambitions, they are seldom evaluated on real-volume
and -velocity data streams and, when they are (e.g., RDFLiveNews [21] and SPEED [24]), they
do not approach web-scale performance. Although the proposed research pipelines may not be
optimised for speed, performance-evaluation results suggest that more efficient algorithms are
needed, for example, running on staged and parallel architectures. High-performance technolo-
gies for massively distributed news knowledge graphs are also called for, for example, exploiting
big-graph databases such as PregelA75 and Giraph.A42
News domain: Whereas practical applications of KGs may be driven by economical (for eco-
nomy/finance) and popular (e.g., for sports) interests, there is ample opportunity on the research
side for adapting and tuning existing approaches to new and unexplored domains that have high
societal value. One largely unexplored domain is corruption and political nepotism, along the lines
suggested in Reference [128]. Misinformation is another area of great importance, and in the do-
main of crises and social unrest, the GDELT data streams may offer opportunities.
Language: Research is needed to make semantic KGs for news available for smaller languages.
There is so far little uptake of cross-language models like multi-lingual BERT and little research
on exploiting dedicated language models for smaller languages for news purposes.

4.4 Research Questions

We are now ready to answer the four research questions we posed in the Introduction.
RQ1: Which research problems and approaches are most common, and what are the central results?
Our discussion in Section 4 and Table 6 answers this question for each of the main themes in our
framework. The review shows that research on semantic knowledge graphs for news is highly
diverse and in constant flux as the enabling technologies evolve. A frequent type of paper is one
that develops new tools and techniques for representing news semantically to disseminate news
content more effectively. In response to the increasing societal importance of information quality
and misinformation, there is currently a rapidly growing interest in fake-news detection and fact
checking. The tools and techniques are typically developed as pipelines or prototypes and evalu-
ated using experiments, examples or use cases. The experimental methods used are maturing.
RQ2: Which research problems and approaches have received less attention, and what types of
contributions are rarer? Our discussion in Section 4, and in 4.3, in particular, answers this question
by identifying many under-researched areas. The review shows that there are very few industrial
case studies. In our literature searches, we have found few surveys and reviews. There is also
little research on issues such as privacy, ownership, terms of use, and provenance, although a few
papers mention the latter. Only a few papers focus on evaluating their results in real-time and
big-data settings and, when they do, the results are often in need of improvement. Other green-
field areas include: exploiting location data and data from the Internet of Things, supporting social
and citizen journalism, using semantic knowledge graphs to identify new newsworthy events as
in Reuters Tracer,A73 and using semantic knowledge graphs to construct narratives and generate
news content.
Although the results suggest that semantic knowledge graphs can indeed support better organ-
isation, management, retrieval, and dissemination of news content, there is still a potential for
much larger uptake in industry. Empirical studies are needed to explain why. One possible explan-
ation is that there is a mismatch between what the current tools and algorithms offer and what
the industry needs. Another possible explanation is that the solutions themselves are immature,
for example, that existing analysis techniques are not sufficiently precise or that the often crowd-
sourced reference and training data used are perceived as less trustworthy.

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:31

RQ3: How is the research evolving? Our analysis in Section 3.13 answers this question by showing
that the research broadly follows the development of the supporting technologies used. We identify
four eras in the evolution of KGs for news, characterised by (1) applying early Semantic-Web
ideas to the news domain, (2) exploiting the Linked Open Data (LOD) cloud for news purposes,
(3) semantic knowledge graphs and machine learning and, most recently, (4) deep-learning ap-
proaches based on semantic knowledge graphs.
RQ4: Which are the most frequently cited papers and projects, and which papers and pro-
jects are citing one another? Our analyses in Sections 3.11 and 3.12 answer this question. The
most cited papers are the ones about DKN [73] and KIM [37]. Many recent papers that use
deep-learning techniques for fake-news detection or recommendation are already much cited, e.g.,
References [52, 69]. Among the central projects, main papers related to the Hermes [4], News-
Reader [72], and NEWS [15] projects have been most cited. Another much-referenced group of
papers centres around what we have called the “MediaLoep” collaboration. The citation analysis
reported in the online Addendum (Figure 10) shows that the main paper from the Neptuno pro-
ject [7] and the effort to make IPTC’s news architectureA66 semantic [71] also are important.

4.5 Limitations
The most central limitation of our literature review is its scope. We only consider papers that use
semantic knowledge graphs or related semantic techniques for news-related purposes, excluding
papers that attempt to solve similar problems using other knowledge representation techniques or
targeting other domains. There is also a growing body of research on representing texts in general
as semantic knowledge graphs, proposing techniques and tools that could also be used to analyse
news. There is another growing body of research on supporting news with knowledge graphs that
are not semantically linked, i.e., with knowledge graphs whose nodes and edges do not link into
the LOD cloud.

5 CONCLUSION
We have reported a systematic literature review of research on how semantic knowledge graphs
can be used to facilitate all aspects of production, dissemination, and consumption of news. Starting
with more than 6,000 papers, we identified 80 main papers that we analysed in depth according
to an analysis framework that we kept refining as analysis progressed. As a result, we have been
able answer research questions about past, current, and emerging research areas and trends, and
Section 4.3 has offered many paths for further work. We hope the results of our study will be useful
for practitioners and researchers who are interested specifically in semantic knowledge graphs for
news or more generally in computational journalism or in semantic knowledge graphs.

CONFLICT OF INTEREST
The authors are themselves involved in the News Angler project reported in Reference [46].

MAIN PAPERS
[1] Adeel Ahmed and Syed Saif. 2017. DBpedia based ontological concepts driven information extraction from unstruc-
tured text. Int. J. Adv. Comput. Sci. Applic. 8, 9 (2017). DOI:https://doi.org/10.14569/IJACSA.2017.080954
[2] Alessio Antonini, Ruggero G. Pensa, Maria Luisa Sapino, Claudio Schifanella, Raffaele Teraoni Prioletti, and Luca
Vignaroli. 2013. Tracking and analyzing TV content on the web through social and ontological knowledge. In
Proceedings of the 11th European Conference on Interactive TV and Video — EuroITV’13. ACM Press, 13. DOI:https://
doi.org/10.1145/2465958.2465978
[3] Francisco Berrizbeita and Maria-Esther Vidal. 2014. Traversing the linking open data cloud to create news from
tweets. In On the Move to Meaningful Internet Systems: OTM 2014 Workshops, Robert Meersman, Hervé Panetto, Alok
Mishra, Rafael Valencia-García, António Lucas Soares, Ioana Ciuciu, Fernando Ferri, Georg Weichhart, Thomas

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:32 A. L. Opdahl et al.

Moser, Michele Bezzi, and Henry Chan (Eds.), Vol. 8842. Springer, Berlin, 479–488. DOI:https://doi.org/10.1007/978-
3-662-45550-0_48
[4] Jethro Borsje, Leonard Levering, and Flavius Frasincar. 2008. Hermes: A semantic web-based news decision support
system. In Proceedings of the ACM Symposium on Applied Computing — SAC’08. ACM Press, 2415. DOI:https://doi.
org/10.1145/1363686.1364258
[5] A. M. Braşoveanu and R. Andonie. 2019. Semantic fake news detection: A machine learning perspective. In Pro-
ceedings of the International Work-Conference on Artificial Neural Networks. Springer, 656–667.
[6] Iván Cantador, Pablo Castells, and Alejandro Bellogín. 2011. An enhanced semantic layer for hybrid recommender
systems: Application to news recommendation. Int. J. Semant. Web Inf. Syst. 7, 1 (2011), 44–78.
[7] Pablo Castells, Ferran Perdrix, E. Pulido, Rico Mariano, R. Benjamins, Jesús Contreras, and J. Lorés. 2004. Neptuno:
Semantic web technologies for a digital newspaper archive. In Proceedings of the European Semantic Web Symposium.
Springer, Berlin, 445–458.
[8] Mohammad Hossein Davarpour, Mohammad Karim Sohrabi, and Milad Naderi. 2019. Toward a semantic-based
location tagging news feed system: Constructing a conceptual hierarchy on geographical hashtags. Comput. Electric.
Eng. 78 (2019), 204–217. DOI:https://doi.org/10.1016/j.compeleceng.2019.07.005
[9] Tom De Nies, Sam Coppens, Davy Van Deursen, Erik Mannens, and Rik Van de Walle. 2012. Automatic discovery
of high-level provenance using semantic similarity. In Provenance and Annotation of Data and Processes (Lecture
Notes in Computer Science), Paul Groth and James Frew (Eds.). Springer, 97–110.
[10] Pedro Debevere, Davy Van Deursen, Dieter Van Rijsselbergen, Erik Mannens, Mike Matton, Robbie De Sutter, and
Rik Van de Walle. 2011. Enabling semantic search in a news production environment. In Semantic Multimedia
(Lecture Notes in Computer Science), Thierry Declerck, Michael Granitzer, Marcin Grzegorzek, Massimo Romanelli,
Stefan Rüger, and Michael Sintek (Eds.). Springer, 32–47.
[11] Mike Dowman, Valentin Tablan, Hamish Cunningham, and Borislav Popov. 2005. Web-assisted annotation, se-
mantic indexing and search of television and radio news. In Proceedings of the 14th International Conference on
World Wide Web. ACM Press, 225. DOI:https://doi.org/10.1145/1060745.1060781
[12] Ludivine Duroyon, François Goasdoué, and Ioana Manolescu. 2019. A linked data model for facts, statements and be-
liefs. In Proceedings of the World Wide Web Conference. ACM, 988–993. DOI:https://doi.org/10.1145/3308560.3316737
[13] Francesca Fallucchi, Rosario Di Stabile, Erasmo Purificato, Romeo Giuliano, and Ernesto William De Luca. 2021.
Enriching videos with automatic place recognition in Google Maps. Multim. Tools Applic. 81 (2021), 23105–23121.
DOI:10.1007/s11042-021-11253-9
[14] Dèlia Fernàndez-Cañellas, Joan Espadaler, David Rodriguez, Blai Garolera, Gemma Canet, Aleix Colom, Joan Marco
Rimmek, Xavier Giro-i Nieto, Elisenda Bou, and Juan Carlos Riveiro. 2019. VLX-Stories: Building an online event
knowledge base with emerging entity detection. In Proceedings of the International Semantic Web Conference
(ISWC’19). Springer, 382–399.
[15] Norberto Fernández, José M. Blázquez, Jesús A. Fisteus, Luis Sánchez, Michael Sintek, Ansgar Bernardi, Manuel
Fuentes, Angelo Marrara, and Zohar Ben-Asher. 2006. NEWS: Bringing semantic web technologies into news agen-
cies. In The Semantic Web — ISWC 2006, David Hutchison, Takeo Kanade, Josef Kittler, Jon M. Kleinberg, Friedemann
Mattern, John C. Mitchell, Moni Naor, Oscar Nierstrasz, C. Pandu Rangan, Bernhard Steffen, Madhu Sudan, Demetri
Terzopoulos, Dough Tygar, Moshe Y. Vardi, Gerhard Weikum, Isabel Cruz, Stefan Decker, Dean Allemang, Chris
Preist, Daniel Schwabe, Peter Mika, Mike Uschold, and Lora M. Aroyo (Eds.), Vol. 4273. Springer, Berlin, 778–791.
DOI:https://doi.org/10.1007/11926078_56
[16] Norberto Fernández, José M. Blázquez, Luis Sánchez, and Ansgar Bernardi. 2007. IdentityRank: Named entity dis-
ambiguation in the context of the NEWS project. In The Semantic Web: Research and Applications, Enrico Franconi,
Michael Kifer, and Wolfgang May (Eds.), Vol. 4519. Springer, Berlin, 640–654. DOI:https://doi.org/10.1007/978-3-
540-72667-8_45
[17] Norberto Fernández, Damaris Fuentes, Luis Sánchez, and Jesús A. Fisteus. 2010. The NEWS ontology: Design and
applications. Exp. Syst. Applic. 37, 12 (2010), 8694–8704.
[18] Michael Färber, Achim Rettinger, and Andreas Harth. 2016. Towards monitoring of novel statements in the news.
In The Semantic Web — Latest Advances and New Domains (Lecture Notes in Computer Science), Harald Sack,
Eva Blomqvist, Mathieu d’Aquin, Chiara Ghidini, Simone Paolo Ponzetto, and Christoph Lange (Eds.). Springer,
285–299.
[19] Jie Gao, Xin Xin, Junshuai Liu, Rui Wang, Jing Lu, Biao Li, Xin Fan, and Ping Guo. 2018. Fine-grained deep
knowledge-aware network for news recommendation with self-attention. In Proceedings of the IEEE/WIC/ACM
International Conference on Web Intelligence (WI). IEEE, 81–88. DOI:https://doi.org/10.1109/WI.2018.0-104
[20] Roberto García, Ferran Perdrix, Rosa Gil, and Marta Oliva. 2008. The semantic web as a newspaper media conver-
gence facilitator. J. Web Semant. 6, 2 (Apr. 2008), 151–161. DOI:https://doi.org/10.1016/j.websem.2008.01.002

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:33

[21] Daniel Gerber, Sebastian Hellmann, Lorenz Bühmann, Tommaso Soru, Ricardo Usbeck, and Axel-Cyrille
Ngonga Ngomo. 2013. Real-time RDF extraction from unstructured data streams. In Proceedings of the International
Semantic Web Conference (ISWC’13). 135–150. DOI:https://doi.org/10.1007/978-3-642-41335-3_9
[22] J. Golbeck and C. Halaschek-Wiener. 2009. Trust-based revision for expressive web syndication. J. Log. Computat.
19, 5 (Oct. 2009), 771–790. DOI:https://doi.org/10.1093/logcom/exn045
[23] A. Groza and A.-D. Pop. 2020. Fake news detector in the medical domain by reasoning with description logics. In
Proceedings of the IEEE 16th International Conference on Intelligent Computer Communication and Processing (ICCP).
145–152. DOI:https://doi.org/10.1109/ICCP51029.2020.9266270
[24] Alexander Hogenboom, Frederik Hogenboom, Flavius Frasincar, Kim Schouten, and Otto van der Meer. 2013.
Semantics-based information extraction for detecting economic events. Multim. Tools Applic. 64, 1 (May 2013),
27–52. DOI:https://doi.org/10.1007/s11042-012-1122-0
[25] Frederik Hogenboom, Damir Vandic, Flavius Frasincar, Arnout Verheij, and Allard Kleijn. 2014. A query language
and ranking algorithm for news items in the Hermes news processing framework. Sci. Comput. Program. 94 (Nov.
2014), 32–52. DOI:https://doi.org/10.1016/j.scico.2013.07.018
[26] Frank Hopfgartner and Joemon M. Jose. 2010. Semantic user profiling techniques for personalised multimedia
recommendation. Multim. Syst. 16, 4–5 (Aug. 2010), 255–274. DOI:https://doi.org/10.1007/s00530-010-0189-6
[27] Klesti Hoxha, Artur Baxhaku, and Ilia Ninka. 2016. Bootstrapping an online news knowledge base. In Web En-
gineering, Alessandro Bozzon, Philippe Cudre-Maroux, and Cesare Pautasso (Eds.), Vol. 9671. Springer, 501–506.
DOI:https://doi.org/10.1007/978-3-319-38791-8_37
[28] I.-Ching Hsu. 2013. Personalized web feeds based on ontology technologies. Inf. Syst. Front. 15, 3 (July 2013),
465–479. DOI:https://doi.org/10.1007/s10796-011-9337-6
[29] Wouter IJntema, Jordy Sangers, Frederik Hogenboom, and Flavius Frasincar. 2012. A lexico-semantic pattern lan-
guage for learning ontology instances from text. J. Web Semant. 15 (2012), 37–50. DOI:https://doi.org/10.1016/j.
websem.2012.01.002
[30] Akshay Java, Sergei Nirneburg, Marjorie McShane, Timothy Finin, Jesse English, and Anupam Joshi. 2007. Using
a natural language understanding system to generate semantic web content. Int. J. Semant. Web Inf. Syst. 3, 4 (Oct.
2007), 50–74. DOI:https://doi.org/10.4018/jswis.2007100103
[31] Yun Jing, Xu Zhiwei, and Gao Guanglai. 2020. Context-driven image caption with global semantic relations of the
named entities. IEEE Access 8 (2020), 143584–143594.
[32] Maarten Jongmans, Viorel Milea, and Flavius Frasincar. 2014. A semantic web approach for visualization-based
news analytics. In Knowledge Management in Organizations, Lorna Uden, Darcy Fuenzaliza Oshee, I-Hsien Ting,
and Dario Liberona (Eds.), Vol. 185. Springer, 195–204. DOI:https://doi.org/10.1007/978-3-319-08618-7_20
[33] Kevin Joseph and Hui Jiang. 2019. Content based news recommendation via shortest entity distance over know-
ledge graphs. In Proceedings of the World Wide Web Conference. ACM, 690–699. DOI:https://doi.org/10.1145/3308560.
3317703
[34] Leonidas Kallipolitis, Vassilis Karpis, and Isambo Karali. 2012. Semantic search in the world news domain us-
ing automatically extracted metadata files. Knowl.-based Syst. 27 (Mar. 2012), 38–50. DOI:https://doi.org/10.1016/j.
knosys.2011.12.007
[35] Walter Kasper, Jörg Steffen, and Yajing Zhang. 2008. News annotations for navigation by semantic similarity. In
Proceedings of KI 2008: Advances in Artificial Intelligence, Andreas R. Dengel, Karsten Berns, Thomas M. Breuel,
Frank Bomarius, and Thomas R. Roth-Berghofer (Eds.), Vol. 5243. Springer, Berlin, 233–240. DOI:https://doi.org/
10.1007/978-3-540-85845-4_29
[36] Haklae Kim. 2017. Building a K-Pop knowledge graph using an entertainment ontology. Knowl. Manag. Res. Pract.
15, 2 (May 2017), 305–315. DOI:https://doi.org/10.1057/s41275-017-0056-8
[37] Atanas Kiryakov, Borislav Popov, Ivan Terziev, Dimitar Manov, and Damyan Ognyanoff. 2004. Semantic annotation,
indexing, and retrieval. J. Web Semant. 2, 1 (Dec. 2004), 49–79. DOI:https://doi.org/10.1016/j.websem.2004.07.005
[38] Erdal Kuzey, Jilles Vreeken, and Gerhard Weikum. 2014. A fresh look on knowledge bases: Distilling named events
from news. In Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge
Management. ACM Press, 1689–1698. DOI:https://doi.org/10.1145/2661829.2661984
[39] Edward H. Y. Lim, Raymond S. T. Lee, and James N. K. Liu. 2008. KnowledgeSeeker — An ontological agent-based
system for retrieving and analyzing Chinese web articles. In Proceedings of the IEEE International Conference on
Fuzzy Systems (IEEE World Congress on Computational Intelligence). IEEE, 1034–1041. DOI:https://doi.org/10.1109/
FUZZY.2008.4630497
[40] Danyang Liu, Jianxun Lian, Zheng Liu, Xiting Wang, Guangzhong Sun, and Xing Xie. 2021. Reinforced anchor
knowledge graph generation for news recommendation reasoning. In Proceedings of the 27th ACM SIGKDD Con-
ference on Knowledge Discovery & Data Mining. 1055–1065.

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:34 A. L. Opdahl et al.

[41] Jue Liu, Zhuocheng Lu, and Wei Du. 2019. Combining enterprise knowledge graph and news sentiment analysis
for stock price prediction. In Proceedings of the 52nd Hawaii International Conference on System Sciences.
[42] Jinshuo Liu, Chenyang Wang, Chenxi Li, Ningxi Li, Juan Deng, and Jeff Z. Pan. 2021. DTN: Deep triple network
for topic specific fake news detection. J. Web Semant. 70 (2021), 100646. DOI:10.1016/j.websem.2021.100646
[43] Eduardo Lupiani-Ruiz, Ignacio García-Manotas, Rafael Valencia-García, Francisco García-Sánchez, Dagoberto
Castellanos-Nieves, Jesualdo Tomás Fernández-Breis, and Juan Bosco Camón-Herrero. 2011. Financial news se-
mantic search engine. Exp. Syst. Applic. 38, 12 (Nov. 2011), 15565–15572. DOI:https://doi.org/10.1016/j.eswa.2011.
06.003
[44] Erik Mannens, Sam Coppens, Toon De Pessemier, Hendrik Dacquin, Davy Van Deursen, Robbie De Sutter, and Rik
Van de Walle. 2013. Automatic news recommendations via aggregated profiling. Multim. Tools Applic. 63, 2 (Mar.
2013), 407–425. DOI:https://doi.org/10.1007/s11042-011-0844-8
[45] Qianren Mao, Xi Li, Hao Peng, Jianxin Li, Dongxiao He, Shu Guo, Min He, and Lihong Wang. 2021. Event prediction
based on evolutionary event ontology knowledge. Fut. Gen. Comput. Syst. 115 (2021), 76–89.
[46] Enrico Motta, Enrico Daga, Andreas L. Opdahl, and Bjørnar Tessem. 2020. Analysis and design of computational
news angles. IEEE Access 8 (2020), 120613–120626.
[47] Saikat Mukherjee, Guizhen Yang, and I. V. Ramakrishnan. 2003. Automatic annotation of content-rich HTML doc-
uments: Structural and semantic analysis. In The Semantic Web — ISWC 2003, Gerhard Goos, Juris Hartmanis,
Jan van Leeuwen, Dieter Fensel, Katia Sycara, and John Mylopoulos (Eds.), Vol. 2870. Springer, Berlin, 533–549.
DOI:https://doi.org/10.1007/978-3-540-39718-2_34
[48] Eric Müller-Budack, Jonas Theiner, Sebastian Diering, Maximilian Idahl, and Ralph Ewerth. 2020. Multimodal ana-
lytics for real-world news using measures of cross-modal entity consistency. In Proceedings of the International
Conference on Multimedia Retrieval. ACM, 16–25. DOI:https://doi.org/10.1145/3372278.3390670
[49] Quang-Minh Nguyen and Tuan-Dung Cao. 2015. A novel approach for automatic extraction of semantic data about
football transfer in sport news. Int. J. Pervas. Comput. Commun. 11, 2 (2015), 233–252. DOI:https://doi.org/10.1108/
IJPCC-03-2015-0018 WOS:000212340300007.
[50] Quang-Minh Nguyen, Thanh-Tam Nguyen, and Tuan-Dung Cao. 2016. Semantic-based recommendation for sport
news aggregation system. In Research and Practical Issues of Enterprise Information Systems (Lecture Notes in Busi-
ness Information Processing), A Min Tjoa, Li Da Xu, Maria Raffai, and Niina Maarit Novak (Eds.). Springer, 32–47.
[51] Inna Novalija and Dunja Mladenić. 2013. Applying semantic technology to business news analysis. Appl. Artif.
Intell. 27, 6 (July 2013), 520–550. DOI:https://doi.org/10.1080/08839514.2013.805600
[52] Jeff Z. Pan, Siyana Pavlova, Chenxi Li, Ningxi Li, Yangmei Li, and Jinshuo Liu. 2018. Content based fake news de-
tection using knowledge graphs. In The Semantic Web — ISWC 2018, Denny Vrandečić, Kalina Bontcheva, Mari Car-
men Suárez-Figueroa, Valentina Presutti, Irene Celino, Marta Sabou, Lucie-Aimée Kaffee, and Elena Simperl (Eds.),
Vol. 11136. Springer, 669–683. DOI:https://doi.org/10.1007/978-3-030-00671-6_39
[53] Koralia Papadokostaki, Stavros Charitakis, George Vavoulas, Stella Panou, Paraskevi Piperaki, Aris Papakon-
stantinou, Savvas Lemonakis, Anna Maridaki, Konstantinos Iatrou, Piotr Arent, Dawid Wiśniewski, Nikos Papada-
kis, and Haridimos Kondylakis. 2017. News articles platform: Semantic tools and services for aggregating and ex-
ploring news articles. In Strategic Innovative Marketing (Springer Proceedings in Business and Economics), Androniki
Kavoura, Damianos P. Sakas, and Petros Tomaras (Eds.). Springer, 511–519.
[54] Marco Ponza, Diego Ceccarelli, Paolo Ferragina, Edgar Meij, and Sambhav Kothari. 2021. Contextualizing trending
entities in news stories. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining.
346–354.
[55] Radityo Eko Prasojo, Mouna Kacimi, and Werner Nutt. 2018. Modeling and summarizing news events using se-
mantic triples. In The Semantic Web (Lecture Notes in Computer Science), Aldo Gangemi, Roberto Navigli, Maria-
Esther Vidal, Pascal Hitzler, Raphaël Troncy, Laura Hollink, Anna Tordai, and Mehwish Alam (Eds.). Springer,
512–527.
[56] Kira Radinsky, Sagie Davidovich, and Shaul Markovitch. 2012. Learning causality for news events prediction. In
Proceedings of the 21st International Conference on World Wide Web (WWW’12). ACM Press, 909–918. DOI:https:
//doi.org/10.1145/2187836.2187958
[57] D. B. Ramagem, B. Margerin, and J. Kendall. 2004. AnnoTerra: Building an integrated earth science resource using
semantic web technologies. IEEE Intell. Syst. 19, 3 (May 2004), 48–57. DOI:https://doi.org/10.1109/MIS.2004.3
[58] Wouter Rijvordt, Frederik Hogenboom, and Flavius Frasincar. 2019. Ontology-driven news classification with
Aethalides. J. Web Eng. 18, 7 (2019), 627–654. DOI:https://doi.org/10.13052/jwe1540-9589.1873
[59] Marco Rospocher, Marieke van Erp, Piek Vossen, Antske Fokkens, Itziar Aldabe, German Rigau, Aitor Soroa,
Thomas Ploeger, and Tessel Bogaard. 2016. Building event-centric knowledge graphs from news. J. Web Semant.
37-38 (Mar. 2016), 132–151. DOI:https://doi.org/10.1016/j.websem.2015.12.004

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:35

[60] Charlotte Rudnik, Thibault Ehrhart, Olivier Ferret, Denis Teyssou, Raphaël Troncy, and Xavier Tannier. 2019.
Searching news articles using an event knowledge graph leveraged by Wikidata. In Proceedings of the World Wide
Web Conference. 1232–1239.
[61] Tomer Sagi, Yael Wolf, and Katja Hose. 2019. How new is the (RDF) news? In Proceedings of the World Wide Web
Conference. 714–721.
[62] Daniel Sarmiento Suárez and Claudia Jiménez-Guarín. 2014. Natural language processing for linking online news
and open government data. In Advances in Conceptual Modeling, Marta Indulska and Sandeep Purao (Eds.), Vol. 8823.
Springer, 243–252. DOI:https://doi.org/10.1007/978-3-319-12256-4_26
[63] A. Scharl, D. Herring, W. Rafelsberger, A. Hubmann-Haidvogel, R. Kamolov, D. Fischl, M. Föls, and A. Weichsel-
braun. 2017. Semantic systems and visual tools to support environmental communication. IEEE Syst. J. 11, 2 (June
2017), 762–771. DOI:https://doi.org/10.1109/JSYST.2015.2466439
[64] Kim Schouten, Philip Ruijgrok, Jethro Borsje, Flavius Frasincar, Leonard Levering, and Frederik Hogenboom. 2010.
A semantic web-based approach for personalizing news. In Proceedings of the ACM Symposium on Applied Comput-
ing (SAC’10). ACM Press, 854. DOI:https://doi.org/10.1145/1774088.1774264
[65] Md. Hanif Seddiqui, Md. Nesarul Hoque, and Md. Hasan Hafizur Rahman. 2015. Semantic annotation of Bangla
news stream to record history. In Proceedings of the 18th International Conference on Computer and Information
Technology (ICCIT). IEEE, 566–572. DOI:https://doi.org/10.1109/ICCITechn.2015.7488135
[66] Heng-Shiou Sheu, Zhixuan Chu, Daiqing Qi, and Sheng Li. 2021. Knowledge-guided article embed-
ding refinement for session-based news recommendation. IEEE Trans. Neural Netw. Learn. Syst. (2021).
DOI:10.1109/TNNLS.2021.3084958
[67] K. Srinivasa and P. Santhi Thilagam. 2019. Crime base: Towards building a knowledge base for crime entities and
their relationships from online news papers. Inf. Process. Manag. 56, 6 (2019), 102059. DOI:https://doi.org/10.1016/
j.ipm.2019.102059
[68] Andrei Tamilin, Bernardo Magnini, Luciano Serafini, Christian Girardi, Mathew Joseph, and Roberto Zanoli. 2010.
Context-driven semantic enrichment of Italian news archive. In The Semantic Web: Research and Applications, David
Hutchison, Takeo Kanade, Josef Kittler, Jon M. Kleinberg, Friedemann Mattern, John C. Mitchell, Moni Naor, Oscar
Nierstrasz, C. Pandu Rangan, Bernhard Steffen, Madhu Sudan, Demetri Terzopoulos, Doug Tygar, Moshe Y. Vardi,
Gerhard Weikum, Lora Aroyo, Grigoris Antoniou, Eero Hyvönen, Annette ten Teije, Heiner Stuckenschmidt, Lili-
ana Cabral, and Tania Tudorache (Eds.), Vol. 6088. Springer, Berlin, 364–378. DOI:https://doi.org/10.1007/978-3-
642-13486-9_25
[69] Andon Tchechmedjiev, Pavlos Fafalios, Katarina Boland, Stefan Dietze, Benjamin Zapilko, and Konstantin Todorov.
2019. ClaimsKG: A live knowledge graph of fact-checked claims. In Proceedings of the 18th International Semantic
Web Conference (ISWC’19), Auckland, New Zealand.
[70] Yu Tian, Yuhao Yang, Xudong Ren, Pengfei Wang, Fangzhao Wu, Qian Wang, and Chenliang Li. 2021. Joint know-
ledge pruning and recurrent graph convolution for news recommendation. In Proceedings of the 44th International
ACM SIGIR Conference on Research and Development in Information Retrieval. 51–60.
[71] Raphaël Troncy. 2008. Bringing the IPTC news architecture into the semantic web. In The Semantic Web — ISWC
2008. Springer, 483–498.
[72] Piek Vossen, Rodrigo Agerri, Itziar Aldabe, Agata Cybulska, Marieke van Erp, Antske Fokkens, Egoitz Laparra,
Anne-Lyse Minard, Alessio Palmero Aprosio, German Rigau, Marco Rospocher, and Roxane Segers. 2016. News-
Reader: Using knowledge resources in a cross-lingual reading machine to generate more knowledge from massive
streams of news. Knowl.-based Syst. 110 (Oct. 2016), 60–85. DOI:https://doi.org/10.1016/j.knosys.2016.07.013
[73] Hongwei Wang, Fuzheng Zhang, Xing Xie, and Minyi Guo. 2018. DKN: Deep knowledge-aware network for news
recommendation. In Proceedings of the World Wide Web Conference. 1835–1844. Retrieved from http://arxiv.org/abs/
1801.08284.
[74] Youze Wang, Shengsheng Qian, Jun Hu, Quan Fang, and Changsheng Xu. 2020. Fake news detection via knowledge-
driven multimodal graph convolutional networks. In Proceedings of the International Conference on Multimedia
Retrieval. 540–547.
[75] Yueji Yang, Yuchen Li, and Anthony K. H. Tung. 2021. NewsLink: Empowering intuitive news search with know-
ledge graphs. In Proceedings of the IEEE 37th International Conference on Data Engineering (ICDE). IEEE, 876–887.
[76] Ryohei Yokoo, Takahiro Kawamura, and Akihiko Ohsuga. 2016. Semantics-based news delivering service. Int. J.
Semant. Comput. 10, 04 (Dec. 2016), 445–459. DOI:https://doi.org/10.1142/S1793351X1640016X
[77] SoYeop Yoo and OkRan Jeong. 2020. Automating the expansion of a knowledge graph. Exp. Syst. Applic. 141 (Mar.
2020), 112965. DOI:https://doi.org/10.1016/j.eswa.2019.112965
[78] Jingyuan Zhang, Chun-Ta Lu, Bokai Cao, Yi Chang, and Philip S. Yu. 2017. Connecting emerging relationships
from news via tensor factorization. In Proceedings of the IEEE International Conference on Big Data (Big Data). IEEE,
1223–1232. DOI:https://doi.org/10.1109/BigData.2017.8258048

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:36 A. L. Opdahl et al.

[79] Jingyuan Zhang, Chun-Ta Lu, Mianwei Zhou, Sihong Xie, Yi Chang, and Philip S. Yu. 2016. HEER: Heterogeneous
graph embedding for emerging relation detection from news. In Proceedings of the IEEE International Conference
on Big Data (Big Data). IEEE, 803–812. DOI:https://doi.org/10.1109/BigData.2016.7840673
[80] Biru Zhu, Xingyao Zhang, Ming Gu, and Yangdong Deng. 2021. Knowledge enhanced fact checking and verification.
IEEE/ACM Trans. Audio, Speech Lang. Process. 29 (2021), 3132–3143.

REFERENCES
[81] Jae-wook Ahn, Peter Brusilovsky, Jonathan Grady, Daqing He, and Sue Yeon Syn. 2007. Open user profiles for
adaptive news systems: Help or harm? In Proceedings of the 16th International Conference on World Wide Web.
11–20.
[82] Tareq Al-Moslmi, Marc Gallofré Ocaña, Andreas L. Opdahl, and Csaba Veres. 2020. Named entity extraction for
knowledge graphs: A literature overview. IEEE Access 8 (2020), 32862–32881.
[83] Dean Allemang, James Hendler, and Fabien Gandon. 2020. Semantic Web for the Working Ontologist. Elsevier.
[84] Luigi Atzori, Antonio Iera, and Giacomo Morabito. 2010. The internet of things: A survey. Comput. Netw. 54, 15
(2010), 2787–2805.
[85] Sören Auer, Christian Bizer, Georgi Kobilarov, Jens Lehmann, Richard Cyganiak, and Zachary Ives. 2007. DBpedia:
A nucleus for a web of open data. In The Semantic Web. Springer, 722–735.
[86] Tim Berners-Lee, James Hendler, and Ora Lassila. 2001. The semantic web. Sci. Amer. 284, 5 (2001), 34–43.
[87] Christian Bizer, Tom Heath, and Tim Berners-Lee. 2011. Linked data: The story so far. In Semantic Services, Inter-
operability and Web Applications: Emerging Concepts. IGI Global, 205–227.
[88] Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: A collaboratively cre-
ated graph database for structuring human knowledge. In Proceedings of the ACM SIGMOD International Conference
on Management of Data. 1247–1250.
[89] Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating
embeddings for modeling multi-relational data. Adv. Neural Inf. Process. Syst. 26 (2013), 2787–2795.
[90] Virginia Braun and Victoria Clarke. 2014. What can “thematic analysis” offer health and wellbeing researchers?
Int. J. Qualitat. Stud. Health Well-being 9, 1 (2014), 1–2. DOI:https://doi.org/10.3402/qhw.v9.26152
[91] Hongyun Cai, Vincent W. Zheng, and Kevin Chen-Chuan Chang. 2018. A comprehensive survey of graph embed-
ding: Problems, techniques, and applications. IEEE Trans. Knowl. Data Eng. 30, 9 (2018), 1616–1637.
[92] David Caswell and Chris W. Anderson. 2019. Computational journalism. In The International Encyclopedia of Journ-
alism Studies. Wiley Online Library, 1–8.
[93] Vinay Chaudhri, Chaitanya Baru, Naren Chittar, Xin Dong, Michael Genesereth, James Hendler, Aditya Kalyan-
pur, Douglas Lenat, Juan Sequeda, Denny Vrandečić, et al. 2022. Knowledge graphs: Introduction, history and,
perspectives. AI Mag. 43, 1 (2022), 17–29.
[94] Hamish Cunningham. 2002. GATE: A framework and graphical development environment for robust NLP tools and
applications. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL’02).
168–175.
[95] Hamish Cunningham. 2002. GATE, a general architecture for text engineering. Comput. Human. 36, 2 (2002), 223–
254.
[96] Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of deep bidirectional
transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018).
[97] Nicholas Diakopoulos. 2017. Computational journalism and the emergence of news platforms. In The Routledge
Companion to Digital Journalism Studies. Routledge London, UK, 176–184.
[98] Christiane Fellbaum. 2000. WordNet: An electronic lexical database. Language 76 (2000), 706.
[99] Dieter Fensel, Umutcan Şimşek, Kevin Angele, Elwin Huaman, Elias Kärle, Oleksandra Panasiuk, Ioan Toma, Jürgen
Umbrich, and Alexander Wahler. 2020. Introduction: What is a knowledge graph? In Knowledge Graphs. Springer,
1–10.
[100] Marc Gallofré Ocaña and Andreas Lothe Opdahl. 2021. Developing a software reference architecture for journalistic
knowledge platforms. In Proceedings of the 15th European Conference on Software Architecture (ECSA’21). Technical
University of Aachen/CEUR Workshop Proceedings.
[101] Aldo Gangemi, Valentina Presutti, Diego Reforgiato Recupero, Andrea Giovanni Nuzzolese, Francesco Draicchio,
and Misael Mongiovì. 2017. Semantic web machine reading with FRED. Semant. Web 8, 6 (2017), 873–893.
[102] Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio. 2016. Deep Learning. The MIT Press.
[103] Palash Goyal and Emilio Ferrara. 2018. Graph embedding techniques, applications, and performance: A survey.
Knowl.-Based Syst. 151 (2018), 78–94.
[104] Claudio Gutiérrez and Juan F. Sequeda. 2021. Knowledge graphs. Commun. ACM 64, 3 (2021), 96–104.
[105] Bahareh Rahmanzadeh Heravi and Jarred McGinnis. 2015. Introducing social semantic journalism. J. Media Innov.
2, 1 (2015), 131–140.
ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
Semantic Knowledge Graphs for the News: A Review 140:37

[106] Aidan Hogan, Eva Blomqvist, Michael Cochez, Claudia d’Amato, Gerard de Melo, Claudio Gutierrez, Sabrina
Kirrane, José Emilio Labra Gayo, Roberto Navigli, Sebastian Neumaier, et al. 2021. Knowledge graphs. Synth. Lect.
Data, Semant. Knowl. 12, 2 (2021), 1–257.
[107] Frederik Hogenboom, Flavius Frasincar, Uzay Kaymak, and Franciska De Jong. 2011. An overview of event extrac-
tion from text. In Proceedings of the Workshop on Detection, Representation, and Exploitation of Events in the Semantic
Web (DeRiVE 2011) at 10th International Semantic Web Conference (ISWC 2011), Vol. 779. Citeseer, 48–57.
[108] Alan Jackoway, Hanan Samet, and Jagan Sankaranarayanan. 2011. Identification of live news events using Twitter.
In Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Location-based Social Networks. ACM, 25–32.
[109] Akshay Java, Tim Finin, Sergei Nirenburg, et al. 2006. SemNews: A semantic news framework. In Proceedings of
the 21st National Conference on Artificial Intelligence (AAAI’06). 1939–1940.
[110] Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, and Jun Zhao. 2015. Knowledge graph embedding via dynamic
mapping matrix. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and
the 7th International Joint Conference on Natural Language Processing. 687–696.
[111] Barbara Kitchenham. 2004. Procedures for Performing Systematic Reviews. Technical Report 33. Keele, UK, Keele
University. 1–26 pages.
[112] Douglas B. Lenat. 1995. CYC: A large-scale investment in knowledge infrastructure. Commun. ACM 38, 11 (1995),
33–38.
[113] Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, and Xuan Zhu. 2015. Learning entity and relation embeddings
for knowledge graph completion. In Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI’15).
AAAI Press, 2181–2187.
[114] Marcel Machill and Markus Beiler. 2009. The importance of the Internet for journalistic research: A multi-method
study of the research performed by journalists working for daily newspapers, radio, television and online. Journal.
Stud. 10, 2 (2009), 178–203.
[115] Neil Maiden, Konstantinos Zachos, Amanda Brown, George Brock, Lars Nyre, Aleksander Nygård Tonheim, Di-
mitris Apsotolou, and Jeremy Evans. 2018. Making the news: Digital creativity support for journalists. In Proceed-
ings of the CHI Conference on Human Factors in Computing Systems. ACM, 475.
[116] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S. Corrado, and Jeff Dean. 2013. Distributed representations of
words and phrases and their compositionality. Adv. Neural Inf. Process. Syst. 26 (2013), 3111–3119.
[117] George A. Miller. 1995. WordNet: A lexical database for English. Commun. ACM 38, 11 (1995), 39–41.
[118] Andrey Miroshnichenko. 2018. AI to bypass creativity. Will robots replace journalists? (The answer is “yes”). In-
formation 9, 7 (2018), 183.
[119] Andreas C. Müller and Sarah Guido. 2016. Introduction to Machine Learning with Python: A Guide for Data Scientists.
O’Reilly Media, Inc.
[120] Benedito Medeiros Neto, Edison Ishikawa, George Ghinea, and Tor-Morten Grønli. 2019. Newsroom 3.0: Managing
technological and media convergence in contemporary newsrooms. In Proceedings of the 52nd Hawaii International
Conference on System Sciences.
[121] Natasha Noy, Yuqing Gao, Anshu Jain, Anant Narayanan, Alan Patterson, and Jamie Taylor. 2019. Industry-scale
knowledge graphs: Lessons and challenges. Commun. ACM 62, 8 (2019), 36–43.
[122] Lars Nyre, Solveig Bjørnestad, Bjørnar Tessem, and Kjetil Vaage Øie. 2012. Locative journalism: Designing a
location-dependent news medium for smartphones. Convergence 18, 3 (2012), 297–314.
[123] Andreas L. Opdahl and Bjørnar Tessem. 2020. Ontologies for finding journalistic angles. Softw. Syst. Model. 20, 1
(2020), 71–87. DOI:10.1007/s10270-020-00801-w
[124] Kosmas Panagiotidis and Andreas Veglis. 2020. Transitions in journalism — Toward a semantic-oriented technolo-
gical framework. Journal. Media 1 (2020), 1.
[125] Tassilo Pellegrini. 2012. Semantic metadata in the news production process: Achievements and challenges. In Pro-
ceeding of the 16th International Academic MindTrek Conference (MindTrek’12). Association for Computing Ma-
chinery, New York, NY, USA, 125–133. DOI:10.1145/2393132.2393158
[126] Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. GloVe: Global vectors for word representation.
In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). 1532–1543.
[127] Borislav Popov, Atanas Kiryakov, Angel Kirilov, Dimitar Manov, Damyan Ognyanoff, and Miroslav Goranov. 2003.
KIM — Semantic annotation platform. In Proceedings of the International Semantic Web Conference. Springer, 834–
849.
[128] Borislav Popov, Atanas Kiryakov, Damyan Ognyanoff, Dimitar Manov, and Angel Kirilov. 2004. KIM — A semantic
platform for information extraction and retrieval. Nat. Lang. Eng. 10, 3–4 (2004), 375–392.
[129] Ramón Salaverría. 2019. Digital journalism. In The International Encyclopedia of Journalism Studies. Wiley Online
Library, 1–11.

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.
140:38 A. L. Opdahl et al.

[130] Luis Sánchez-Fernández, Norberto Fernández-García, Ansgar Bernardi, Lars Zapf, Anselmo Penas, and Manuel
Fuentes. 2005. An experience with semantic web technologies in the news domain. In Proceedings of the Workshop
on Semantic Web Case Studies and Best Practices for eBusiness.
[131] Amit Sheth and Krishnaprasad Thirunarayan. 2012. Semantics empowered Web 3.0: Managing enterprise, social,
sensor, and cloud-based data and services for advanced applications. Synth. Lect. Data Manag. 4, 6 (2012), 1–175.
[132] Fabian M. Suchanek, Gjergji Kasneci, and Gerhard Weikum. 2007. YAGO: A core of semantic knowledge. In Pro-
ceedings of the 16th International Conference on World Wide Web. 697–706.
[133] Bjørnar Tessem, Lars Nyre, Michel D. S. Mesquita, and Paul Mulholland. 2022. Deep learning to encourage citizen
involvement in local journalism. In Futures of Journalism, V. J. E. Manninen, M. K. Niemi, and A. Ridge-Newman
(Eds.). Palgrave Macmillan, 211–226. DOI:https://doi.org/10.1007/978-3-030-95073-6_14
[134] Neil Thurman. 2019. Computational journalism. In The Handbook of Journalism Studies (2nd ed.). Routledge, New
York, 475.
[135] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and
Illia Polosukhin. 2017. Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017), 5998–6008.
[136] Zhen Wang, Jianwen Zhang, Jianlin Feng, and Zheng Chen. 2014. Knowledge graph embedding by translating on
hyperplanes. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 28.

Received 25 January 2021; revised 16 May 2022; accepted 23 May 2022

ACM Computing Surveys, Vol. 55, No. 7, Article 140. Publication date: December 2022.