Articles
[en] Augmenting Access to Embodied Knowledge Archives: A Computational FrameworkGiacomo Alliata, Laboratory for Experimental Museology, EPFL, Switzerland; Yumeng Hou, Laboratory for Experimental Museology, EPFL, Switzerland; Sarah Kenderdine, Laboratory for Experimental Museology, EPFL, Switzerland
Abstract
[en]
With the burgeoning use of digital technologies in safeguarding intangible and living heritage, memory institutions have produced a significant body
of material yet to be made accessible for public transmission. The quest for new ways to unlock these massive collections has intensified,
especially in the case of embodied knowledge embedded in complex formats, such as audiovisual and motion capture data.
This study examines a computational workflow that combines posture recognition and movement computing to bridge the gap in accessing digital
archives that capture living knowledge and embodied experiences. By reflecting on how embodied knowledge is sustained and potentially
valorised through human interaction, we devise a series of methods utilising vision-based feature extraction, pose estimation, movement analysis,
and machine learning. The goal is to augment the archival experience with new modes of exploration, representation, and embodiment.
This article reports the computational procedures and algorithmic tools inspected through two use cases. In the first example, we visualise the
archives of the Prix de Lausanne, a collection of 50 years of video recordings of dance performances, for archival exploration through
the dancers' poses. In another experiment, movement encoding is employed to allow multimodal data search via embodied cues in the
Hong Kong Martial Arts Living Archive, a comprehensive documentation of the living heritage of martial arts that is chiefly comprised
of motion-captured performances by masters.
Though holding different application purposes, both projects operate on the proposed framework and extract archive-specific features to create a
meaningful representation of human bodies, which reveals the versatile applications that computational capacities can achieve for embodied knowledge
archives. The practices also represent a model of interdisciplinary involvement where the archivists, computists, artists, and knowledge holders
join hands to renew strategies for archival exploration and heritage interpretation in a new light.
[en] Sensitivity and Access: Unlocking the Colonial Visual Archive with Machine LearningJonathan Dentler, Catholic University of Paris; German Historical Institute, Washington D.C.; Lise Jaillant, Loughborough University, UK; Daniel Foliard, Université Paris Cité, LARCA (UMR 8225); Julien Schuh, Université Paris Nanterre; Maison des Sciences de l'Homme Mondes
Abstract
[en]
In recent decades, archival institutions have digitized an enormous quantity of material under the rubric of open access, including from
colonial archives. However, much of the most sensitive material from these collections remains undigitized or difficult to discover and
use. More recently, a critical reconsideration of open digital access has also taken place, particularly when it comes to sensitive
material from the colonial archive. Collectively, this has created a situation in which the colonial photography archive risks becoming
overly sanitized as well as difficult to navigate and analyze.
In this article, we propose that critical and transparent multimodal artificial intelligence (AI) offers a way to improve access to
colonial archives for researchers and the public, without losing sight of the need for ethical approaches to sensitive visual
materials. The EyCon (Early Conflict Photography and Visual AI) project assembled a large database of sensitive visual materials from
colonial conflicts and developed experimental multi-modal computer vision tools with which to analyze it. Though this tool has not yet
been applied at scale or quantitatively compared with other approaches, we are able to propose modes of inquiry for other researchers to
explore as they create new research tools. On a more hypothetical or theoretical level, we consider how the use of computational tools
to facilitate access to and analysis of sensitive historical materials is compatible with or even beneficial for more ethical approaches
to such materials. We conclude with several promising areas for critically integrating AI into the digital colonial archive, while also
expanding on some limitations of such techniques.
[en] AI and Medical Images: Addressing Ethical Challenges to Provide
Responsible Access to Historical Medical IllustrationsLise Jaillant, Loughborough University, UK; Katherine Aske, Edinburgh Napier University, UK
Abstract
[en]
This article examines the ethical considerations and broader issues around access to digitised historical medical
images. These illustrations and, later, photographs are often extremely sensitive, representing disability, disease,
gender, and race in potentially harmful and problematic ways. In particular, the original metadata for such images can
include demeaning and sometimes racist terms. Some of these images show sexually explicit and violent content, as well
as content that was obtained without informed consent. Hiding these sensitive images can be tempting, and yet, archives
are meant to be used, not locked away. Through a series of interviews with 10 archivists, librarians, and researchers
based in the UK and US, the authors show that improved access to medical illustrations is
essential to produce new knowledge in the humanities and medical research, as well as to bridge the gap between
historical and modern understandings of the human body. Improving access to medical illustration can also help to
address the “gender data gap”, which has acquired mainstream visibility thanks to the work of activists such as
Caroline Criado-Perez, the author of Invisible Women: Data Bias in a World Designed
for Men. Users of historical medical archives are therefore a diverse group, which includes researchers in
medicine, history, and medical and digital humanities, as well as artists, journalists, and activists.
In order to improve discoverability and facilitate access to these archives in an ethical way, this article highlights
the importance of appropriate metadata, which can be enhanced through the use of artificial intelligence (AI) tools.
Indeed, AI can be used to create new metadata when original information is incomplete or is missing altogether, or
when it includes problematic language. AI can also help with the disaggregation of data by gender and/or
racial ethnicity. Moreover, it can recommend similar images to allow users to explore other parts of the collections.
However, AI can also pose issues, for example when it suggests inappropriate metadata or similarity search results.
Keeping humans in the loop is therefore essential when applying AI to sensitive medical images. Ultimately, this article
argues that access to sensitive images cannot be separated from responsibility. Recommendations are made to help
cultural heritage institutions find the right balance, to provide access for research and education, and to also protect
children and other vulnerable audiences from encountering images that can be described as shocking and even
traumatising.
[en] Capturing Captions: Using AI to Identify and Analyse Image Captions in a Large Dataset of Historical Book
IllustrationsJulia Thomas, School of English Communication and Philosophy, Cardiff University; Irene Testini, Special Collections and Archives, Cardiff University
Abstract
[en]
This article outlines how AI methods can be used to identify image captions in a large dataset of digitised historical book illustrations. This
dataset includes over a million images from 68,000 books published between the eighteenth and early twentieth centuries, covering works of
literature, history, geography, and philosophy. The article has two primary objectives. First, it suggests the added value of captions in making
digitized illustrations more searchable by picture content in online archives. To further this objective, we describe the methods we have used to
identify captions, which can effectively be re-purposed and applied in different contexts. Second, we suggest how this research leads to new
understandings of the semantics and significance of the captions of historical book illustrations. The findings discussed here mark a critical
intervention in the fields of digital humanities, book history, and illustration studies.
[en] Deep Learning for Historical Cadastral Maps and Satellite Imagery Analysis:
Insights from Styria's Franciscean CadastreWolfgang Thomas Göderle, University of Innsbruck; Max Planck Institute of Geoanthropology; Fabian Rampetsreiter, University of Graz; Christian Macher, Know Center; Katrin Mauthner, Know Center; Oliver Pimas, Know Center
Abstract
[en]
Cadastres from the 19th century are a complex as well as rich source for historians and archaeologists, the study of which
presents great challenges. For archaeological and historical remote sensing, we have trained several Deep Learning models, CNNs,
and Vision Transformers to extract large-scale data from this knowledge representation. We present the principle results of our
work here and demonstrate our browser-based tool that allows researchers and public stakeholders to quickly identify spots that
featured buildings in the 19th century Franciscean cadastre. The tool not only supports scholars and fellow researchers in
building a better understanding of the settlement history of the region of Styria; it also helps public
administration and fellow citizens to swiftly identify areas of heightened sensibility with regard to the cultural heritage of the
region.
[en] “Open” or “Close” Research Instruments? Conflicting Rationales in the
Organization of Early Digital Medieval History in Europe (1960–1990).Edgar Lejeune, Vossius Center for the History of Humanities and Sciences (University of Amsterdam)
Abstract
[en]
From the late 1940s onwards, humanities scholars used computers in order to create new types of research
instruments, e.g., databases, digital scholarly editions of texts and/or archives, computer programs, etc. Their
ambitions in doing so consisted in saving time in tedious, repetitive and error-prone scholarly tasks, enhancing
the circulation of data and/or scholarly information, or even contributing to the “progress” of an entire
discipline. Sharing these research instruments with interested colleagues was then crucial for these scholars.
However, each of these humanities computing collectives developed at the time its own idiosyncratic procedures for
editing, analyzing, and publishing computer-recorded material. This profoundly affected the possibility for these
research instruments to circulate among scholars.
In this article, I present how medievalists debated about a possible circulation of these digital research
instruments in that context, and how it contributes to the development of an early “humanities computing”
organization in Europe. I show how medievalists’ ambitions raised a whole series of material and intellectual
difficulties which are still essential in our current DH practices and organizations. What data should we edit (and
thus, what data are worth sharing)? In what form should we publish these datasets? And do we need common rules for
this purpose? I argue that a precise history of early DH communities highlights a strong continuity with
contemporary DH issues as well as the importance of historical studies of our field.
[en] Lilypond Music-Notation Software in the Digital-Humanities ToolboxAndrew A. Cashner, University of Rochester
Abstract
[en]
The music-notation software Lilypond generates high-quality music typography from a plain-text input format;
almost every aspect of the program can be customized and programmed, and the system lends itself well to automation
and batch processing. Lilypond offers a “minimal computing” alternative to bloated, costly, and hegemonic
graphical programs. Like many free software tools, however, Lilypond still exacts a cost in time and training
needed to overcome an unwieldly interface and adapt the tool for scholarly purposes. The author developed a system
called lirio that enabled the production of two critical editions and a monograph in
Lilypond (integrated with LaTeX). The system provides a new semantic-markup interface to Lilypond that enables
scholars to think about typography separately from musical content; a range of expanded Lilypond functionality
including incipit staves, mensural coloration brackets, and editorial annotations; and a stricter input format that
makes Lilypond files easier to maintain. The author also developed the prototype ly2mei
compiler to demonstrate how Lilypond files can be converted to MEI-XML, overcoming a major limitation in Lilypond’s
export abilities. The article argues that scholars will be best served by a simple, consistent, meaningful
interface in a format that can be shared and converted. An extension of Lilypond like lirio demonstrates the considerable potential of this tool for enterprising and patient scholars whose
needs are not met by other tools. Lilypond provides a case study for how to make open-source, free-license tools
work for our own needs as digital humanists.
[en] LemonizeTBX: Design and Implementation of a New Converter from TBX to
OntoLex-LemonAndrea Bellandi, Institute for Computational Linguistics "A. Zampolli" CNR, Via Moruzzi 1, 56124, Pisa - Italy; Giorgio Maria Di Nunzio, Department of Information Engineering, University of Padova, Via Gradenigo 6/b, 35131 Padova, Italy; Silvia Piccini, Institute for Computational Linguistics "A. Zampolli" CNR, Via Moruzzi 1, 56124, Pisa - Italy; Federica Vezzani, Department of Linguistic and Literary Studies, University of Padova, Via Elisabetta Vendramini, 13 35137 Padova, Italy
Abstract
[en]
In this paper, we introduce LemonizeTBX, a converter that enhances interoperability between terminological and
lexicographical frameworks, acknowledging their divergent data modelling approaches. First, we present the
theoretical implications of a conversion from the TermBase eXchange (TBX) concept-oriented framework to the
OntoLex-Lemon sense-centred standpoint within Semantic Web technologies. Then, we illustrate the prototype version
of the converter, designed as an interactive tool engaging terminologists in the conversion process.
[en] Towards a National Data Architecture for Cultural Collections: Designing the Australian Cultural Data
EngineRachel Fensham, University of Melbourne; Australian Cultural Data Engine; Tyne Daile Sumner, Australian National University; Australian Cultural Data Engine; Nat Cutter, University of Melbourne; Australian Cultural Data Engine; George Buchanan, RMIT University; Rui Liu, University of Melbourne; Justin Munoz, Independent Scholar; James Smithies, Australian National University; Ivy Zheng, University of Newcastle; David Carlin, RMIT University; Erik Champion, University of South Australia; Hugh Craig, University of Newcastle; Scott East, University of New South Wales; Chris Hay, Flinders University; Lisa M. Given, RMIT University; John Macarthur, University of Queensland; David McMeekin, Curtin University; Joanna Mendelssohn, University of Melbourne; Deborah van der Plaat, University of Queensland
Abstract
[en]
This article summarises the aims, methods, information architecture, outputs, and innovations of the Australian Cultural Data Engine
(ACD-Engine), a project that harnesses leading cultural databases to build bridges to research, industry, and government. The project
investigates digital heritage collections, data ontologies, and interoperability, building an information architecture to enhance the
open sharing of Australian cultural data. Working with a cross-disciplinary team, the ACD-Engine establishes conceptual and technical
frameworks for better understanding the platforms and uses of cultural data across a range of national and international contexts. This
new cyber-infrastructure advances cultural data aggregation and interoperability whilst prioritising data quality and domain
distinctiveness to answer new research questions across disciplines. As such, the ACD-Engine provides a novel approach to data
management and data modelling in the arts and humanities that has significant implications for digital collections, digital humanities,
and data analytics.
[en] Graph based modelling
of prosopographical datasets. Case study: Romans 1by1Rada Varga, Babeș-Bolyai University; Stefan Bornhofen, CY Cergy Paris University
Abstract
[en]
In this paper, we present and discuss a promising research avenue, that is the use of
graph-based models and software for prosopographical data sets. Our case study will
be constituted by Romans 1by1 (http://romans1by1.com/), a digital-born prosopography
focusing on people attested in classical era inscriptions; it presently hosts
approximately 18,000 open access persons files. The project aimed at employing new
techniques and methodologies that come from other fields (i.e. computer science), in
order to approach the study of ancient population in an innovative way, to ease the
research, and to create an open-access tool, available for the academic community. In
the scope of this paper, we use Romans1by1 as an example to explore the perspectives
of ingesting the information from a prosopographical relational database into a graph
database.
[en] From Archive to Database: Using Crowdsourcing, TEI, and Collaborative Labor to Construct the
Maria Edgeworth Letters ProjectHilary Havens, University of Tennessee, Knoxville; Eliza Alexander Wilcox, University of Tennessee, Knoxville; Meredith L. Hale, University of Tennessee, Knoxville; Jamie Kramer, University of Tennessee, Knoxville
Abstract
[en]
This article unpacks the archival, textual, and encoded layers that comprise the Maria Edgeworth Letters Project
(MELP), an open-access digital archive containing the correspondence of the Anglo-Irish Regency author
Maria Edgeworth and her circle. These layers reveal the impossibility of flattening or standardizing our work and instead
advocate for a more inclusive and collaborative digital humanities model that accommodates both institutional and volunteer labor. Just as
different methods were used to approach each archive and manage our project across multiple institutions, each transcription requires a
different level of care, especially as various notes and collaborators are cited in the final project. Through the use of TEI, we can
flexibly represent diverse aspects of each letter while still maintaining a database-readable structure. We endeavor to connect each person,
place, or work identified in Edgeworth's letters and our database to a larger network of linked data in order to place our
project in conversation with other archival resources. For entities that are unidentified or unknown, we create new name authority files
or produce internal data files that can be viewed by our collaborators and users. MELP's flexible structure
thus allows it to strive for interoperability while refusing to efface the individual traces of its collaborators, entities, and material
artifacts.
[en] A Review of James Little’s The Making of Samuel Beckett’s
Not I / Pas moi, That Time /
Cette fois and Footfalls / Pas (2021)Céline Thobois-Gupta, Trinity College Dublin
Abstract
[en]
This review highlights the main achievements of James Little’s The Making of Samuel Beckett’s
Not I / Pas moi, That Time /
Cette fois and Footfalls / Pas (2021).
[en] A Review of Feminist in a Software Lab: Difference +
Design (2018)Diane K. Jakacki, Bucknell University
Abstract
[en]
This review of Feminist in a Software Lab: Difference + Design (2018) considers Tara
McPherson's ambitious and compelling reflections on the Vectors Lab and attendant
journal housed at the University of Southern California, as well as the development of the Scalar web publication environment.
[en] The Humans and Algorithms of Music Recommendation: A Review of Computing Taste (2022)Jacob Pleasants, University of Oklahoma
Abstract
[en]
In Computing Taste, Nick Seaver conducts an anthropological
study of the technologists who design algorithmic music recommendation systems. He
explores their ways of thinking and talking about music, taste, and computation to
better understand their technological design approaches. By highlighting the humans
behind the machines, Computing Taste shows how to think about
computer algorithms as sociotechnical systems.
[en] Digital Methods in Literary Criticism: A Review of Digital Humanities
and Literary Studies (2022)Lili Wang, Harbin Engineering University; Tianxiang Chen, Harbin Engineering University
Abstract
[en]
In Digital Humanities and Literary Studies, Martin Paul
Eve discusses various cases of digital technology in the analysis of literary studies
and examines how digital tools influence literary interpretation. Martin skillfully
navigates the complex landscape of digital methodologies, offering readers a holistic
view of the transformative influence of literary analysis.
