computers

Article
Enhancing Learning Personalization in Educational
Environments through Ontology-Based Knowledge
Representation
William Villegas-Ch * and Joselin García-Ortiz

Escuela de Ingeniería en Ciberseguridad, Facultad de Ingenierías y Ciencias Aplicadas,

Universidad de Las Américas, Quito 170125, Ecuador; jose-lin.garcia.ortiz@udla.edu.ec
* Correspondence: william.villegas@udla.edu.ec; Tel.: +593-98-136-4068

Abstract: In the digital age, the personalization of learning has become a critical priority in education.
This article delves into the cutting-edge of educational innovation by exploring the essential role of
ontology-based knowledge representation in transforming the educational experience. This research
stands out for its significant and distinctive contribution to improving the personalization of learning.
For this, concrete examples of use cases are presented in various academic fields, from formal
education to corporate training and online learning. It is identified how ontologies capture and
organize knowledge semantically, allowing the intelligent adaptation of content, the inference of
activity and resource recommendations, and the creation of highly personalized learning paths. In
this context, the novelty lies in the innovative approach to designing educational ontologies, which
exhaustively considers different use cases and academic scenarios. Additionally, we delve deeper
into the design decisions that support the effectiveness and usefulness of these ontologies for effective
learning personalization. Through practical examples, it is illustrated how the implementation
of ontologies transforms education, offering richer educational experiences adapted to students’
individual needs. This research represents a valuable contribution to personalized education and
Citation: Villegas-Ch, W.;
knowledge management in contemporary educational environments. The novelty of this work
García-Ortiz, J. Enhancing Learning
lies in its ability to redefine and improve the personalization of learning in a constantly evolving
Personalization in Educational
digital world.
Environments through
Ontology-Based Knowledge
Keywords: knowledge representation; ontologies; personalization of learning
Representation. Computers 2023, 12,
199. https://doi.org/10.3390/
computers12100199

Academic Editors: Antonio 1. Introduction

Sarasa Cabezuelo, Covadonga
Education is central to contemporary society and is becoming even more relevant in
Rodrigo San Juan and
Paolo Bellavista
our digital age. The rapid advancement of Information and Communication Technologies
(ICT) has radically transformed how we access and share knowledge. In this context, the
Received: 21 August 2023 personalization of learning emerges as a pressing need since it seeks to adapt teaching to the
Revised: 14 September 2023 needs and preferences of students [1]. Ontology-based knowledge representation appears
Accepted: 15 September 2023 as an innovative tool that can revolutionize education, allowing effective personalization of
Published: 4 October 2023
learning [2]. This article delves into how ontology-based knowledge representation can
drive the personalization of learning in educational environments.
Innovation lies in our ability to create educational experiences more tailored to stu-
Copyright: © 2023 by the authors.
dents’ individual needs. However, achieving true personalization in mass and digital
Licensee MDPI, Basel, Switzerland. educational environments is a complex challenge. This is where ontology-based knowledge
This article is an open access article representation comes into play. This methodology involves the creation of semantic models
distributed under the terms and that capture knowledge in a specific domain [3]. As conceptual structures, ontologies define
conditions of the Creative Commons the relevant entities, their properties, and their relationships. In the educational field, this
Attribution (CC BY) license (https:// translates into creating educational ontologies that model both course content and student
creativecommons.org/licenses/by/ profiles. These ontologies offer a rich and detailed representation of students’ concepts,
4.0/). skills, learning objectives, and preferences.

Computers 2023, 12, 199. https://doi.org/10.3390/computers12100199 https://www.mdpi.com/journal/computers

Computers 2023, 12, 199 2 of 19

The personalization of learning through ontologies is not limited to content adaptation.

It involves inferring each student’s recommendations for activities, learning resources, and
personalized learning paths [4]. Ontology-based reasoning enriches the educational experi-
ence by providing relevant and customized suggestions, thus promoting more effective and
engaged learning. It is essential to integrate heterogeneous data from various sources, such
as online interactions, assessment results, and student feedback [5]. Ontologies provide
a systematic solution that facilitates the integration and analysis of diverse information,
contributing to a more complete understanding of student progress and performance [6].
In education, the integration of advanced technologies and innovative pedagogical
approaches has profoundly transformed how students acquire knowledge and instructors
facilitate learning. One of the most significant developments is the widespread adoption
of Learning Management Systems (LMS), which provide digital platforms for delivering
educational content and resource management. However, the actual effectiveness of an
LMS lies in its ability to personalize students’ learning experiences and enhance instructors’
teaching. This has become a key objective in modern education, and to achieve this,
many have turned to educational ontology. As formally defined knowledge structures,
ontologies offer a promising approach to representing and organizing knowledge in the
educational context.
Although this methodology has the potential to support the personalization of learning,
it also presents considerations such as the complexity of designing and maintaining accurate
educational ontologies, the need for efficient reasoning algorithms, and the importance of
safeguarding the privacy and security of student data [7]. Additionally, this article presents
concrete examples of how ontology-based knowledge representation has been applied in
real-world educational settings. We explore use cases ranging from formal education to
corporate training and online learning.

2. Materials and Methods

In the ever-evolving educational landscape, the concept of personalized learning has
taken center stage, aiming to meet each student’s unique needs and preferences. Ontology-
based knowledge representation is at the heart of this pedagogical transformation, a dy-
namic methodology that reshapes the educational landscape. The method comprehensively
explores how ontologies are fundamental in personalized education. It delves into the intri-
cate role of ontologies in capturing student profiles, including their preferences, learning
goals, and diverse learning styles. Furthermore, it is revealed how ontologies enhance the
adaptation of educational content, the inference of personalized recommendations, and
the development of customized learning paths. To illustrate these concepts in practice,
concrete examples of ontological applications in various educational contexts are reviewed.
These applications demonstrate how ontologies translate into a more effective and relevant
learning experience for students, promoting their academic careers in a highly personalized
and attractive way.

2.1. Literature Review

The personalization of learning has emerged as a fundamental approach in contempo-
rary education, seeking to adapt teaching to student’s individual needs and characteris-
tics. In this context, ontology-based knowledge representation has been highlighted as a
methodology that can transform how personalized education is designed and delivered.
In addition, the personalization of learning has become a central objective in modern
education, driven by the diversity of students and technological possibilities [8]. Tailoring
teaching to students’ preferences, abilities, and needs has been associated with better edu-
cational outcomes and higher motivation. Educational technologies, including learning
management systems (LMS) and online learning platforms, have enabled the collection of
detailed data on student behavior and performance. However, transforming this data into
useful information to personalize instruction remains challenging.
Computers 2023, 12, 199 3 of 19

By examining the existing literature, several works have been identified that address
the personalization of learning through ontology-based knowledge representation. For
example, the results of [9] used ontologies to model the curriculum and student profiles
in an online learning environment. The researcher’s approach allowed the generation of
content and activity recommendations based on mastery and the student’s preferences. The
study described in [10] proposed an ontology representing learning objectives and compe-
tencies in an educational program. They used this ontology to explain the correspondence
between learning objectives and activities.
On the other hand, the work in [11] explores the application of ontologies in evalu-
ation and automated feedback. Its ontology represented the evaluation criteria and the
performance characteristics of the students. By comparing the actual performance with the
requirements defined by the ontology, automatic and personalized feedback was generated
for each student. The study in [12] focused on personalizing learning paths in a corporate
training environment. They used ontologies to model the employees’ skills and preferences,
allowing them to generate learning paths adapted to all.
This proposal differs from previous works by comprehensively addressing the person-
alization of learning, considering both educational content and automated evaluation and
feedback [13].

2.2. Fundamental Concepts for Ontology Development

Building an adequate ontology to represent knowledge in the educational field requires
a clear and precise definition of fundamental concepts. These concepts are essential building
blocks that allow crucial elements to be modeled and related within the academic realm.
Therefore, this paper explores some of the key concepts used in ontology development,
providing a deeper understanding of how educational knowledge has been represented in
a structured way [14].
Educational competencies are skills, knowledge, and abilities students must acquire
during their learning process. These competencies are critical to the achievement of aca-
demic and professional goals [15]. In our ontology, educational competencies have been
modeled as distinct entities, each with attributes that describe their name, description, and
required level of proficiency.
Learning objectives define what students are expected to achieve by completing a
course, module, or educational activity. These goals guide content planning and assess-
ments. In our ontology, learning objectives are represented as instances of a “Learning
Objective” class, each with properties detailing its description, associated competencies,
and level of complexity.
Educational materials include textbooks, presentations, videos, and learning activities.
These resources play a crucial role in the delivery of educational content. In this work,
educational materials have been modeled as instances of an “Educational Material” class,
with attributes that describe their title, type of resource, and related learning objectives.
Students are critical in the educational process; here, they are represented as unique
individuals in the proposed ontology, with attributes that capture their name, identifier,
and acquired competencies [16]. In addition, relationships are established between students
and the learning objectives they have achieved.
Assessments are instruments used to measure student progress and mastery of learn-
ing objectives. The feedback provided to the students after the evaluations is crucial for
continuous improvement. In this ontology, assessments are modeled as instances of an
“Assessment” class, with properties including their description, related learning objectives,
and success criteria.
The ontology is based on relationships and properties linking concepts and establish-
ing semantic connections. We use properties such as “hasCompetency”, “hasLearningObjec-
tive”, and “relatedTo” to establish relationships between competencies, learning objectives,
educational materials, and students. These relationships allow for rich and contextualized
modeling of academic knowledge.
Computers 2023, 12, 199 4 of 19

These concepts and relationships form the basis of our ontology to represent knowl-
edge in the educational field [17]. By coherently defining and structuring these elements,
we have created a robust framework that captures the complexity and interconnectedness
of learning in education.

2.3. Method
The construction of the educational ontology is driven by a series of carefully con-
sidered design decisions, all aimed at optimizing its usefulness and effectiveness in the
educational setting. One critical decision relates to the class hierarchy we established in
the ontology. A hierarchical structure was chosen to reflect the complex and intertwined
nature of the educational environment. For example, the main class, “Plan of Studies”, en-
compasses more specific classes such as “Course”, “Subject”, and “Educational Resources”.
This decision seeks to facilitate the exploration of content at different levels of detail, which,
in turn, enriches the user experience by allowing them to access relevant information
more efficiently.
The selection of properties is a crucial part of the design process. Each property was
carefully chosen to align with the primary objective: to improve the personalization of
learning and knowledge management. An example is the inclusion of the “LearningStyle”.
By allowing students to specify their preferred learning style, this ontology can tailor
resource and activity recommendations to meet each student’s preferences, thus improving
their engagement and understanding.
Another significant aspect is the modeling of relationships through properties. The
addition of the “Taught” property, which establishes the connection between educators and
the courses they teach, demonstrates the focus on understanding the complex interactions
between teachers and students in the educational environment. This, in turn, facilitates the
management and coordination of the courses, benefiting both educators and students.
In addition, the “EducationalLevel” property also plays a key role. This choice makes
it possible to categorize resources and contents according to the different educational
levels, thus attending to each training stage’s specific needs. This level-based personal-
ization ensures that users access information appropriate to their level of knowledge and
understanding, ultimately enriching the quality of the educational experience.

2.3.1. Design of the Educational Ontology

The design of the educational ontology is a crucial step in this proposal to represent
knowledge and manage data in the academic field. Therefore, the design process for
developing an effective and accurate ontology that captures key relationships and concepts
in the educational domain is described in detail.
The first step in designing the educational ontology was identifying the key concepts
in the represented academic field. These concepts include entities such as “Student”,
“Teacher”, “Course”, “Subject”, “Assessment”, and “Educational Resources”. To facilitate
this identification, a review of the educational literature and consultations with experts in
pedagogy are carried out [18]. Once the key concepts have been identified, we define the
classes and properties that will make up the ontology. Here, the Web Ontology Language
(OWL) formalizes these definitions. For example, the “Student” class has been created with
properties such as “name”, “age”, and “enrolled_in”, which establishes the relationship
between a student and the course in which they are enrolled.
A class hierarchy structure is created to organize the concepts and classes in the ontol-
ogy hierarchically. For example, a hierarchy is generated that groups the classes “Course”,
“Subject”, and “Educational Resources” under the superior class of “Plan of Studies”. This
allowed us to represent the relationship between different levels of information in the
educational context [19]. The relations between classes are fundamental in an ontology.
Associations such as “teaches” are designed between the categories “Teacher” and “Course”
to model the relationship of a teacher with the courses they teach. In addition, restrictions
are incorporated to guarantee the coherence and validity of the information represented.
 Studies”. This allowed us to represent the relationship between different levels of infor-
mation in the educational context [19]. The relations between classes are fundamental in
an ontology. Associations such as “teaches” are designed between the categories
“Teacher” and “Course” to model the relationship of a teacher with the courses they teach.
Computers 2023, 12, 199 5 of 19
In addition, restrictions are incorporated to guarantee the coherence and validity of the
information represented. For example, cardinality constraints are established to ensure
that each course has at least one professor and that each student is enrolled in at least one
For example, cardinality constraints are established to ensure that each course has at least
class.
one professor
Flowchartsand that each student
representing is enrolled in
the fundamental at least
classes, one class.and relationships have
properties,
Flowcharts representing the fundamental classes, properties,
been created to visualize and communicate the structure and relationships and relationships have
in the educa-
been created to visualize and communicate the structure and relationships
tional ontology. These figures facilitated the understanding of the ontology design for in the educa-
tional ontology.experts
both ontology These figures facilitated
and academic the understanding of the ontology design for both
professionals.
ontology experts and academic professionals.
Figure 1 shows a simplified example of the flowchart representing the main classes
and Figure 1 shows
relationships in aour
simplified example
educational of theThe
ontology. flowchart representing
flowchart begins withthe the
main classes
“Concept
and relationships in our educational ontology. The flowchart begins with
Definition” step, which involves identifying and describing the critical elements in the the “Concept
Definition” step, which
academic domain. Theseinvolves
conceptsidentifying and describing
include “Student”, “Teacher”,the“Course”,
critical elements
“Subject”,in and
the
academic domain. These concepts include “Student”, “Teacher”, “Course”,
“Assessment”. As you progress through the diagram, you will see the “Relationships and “Subject”, and
“Assessment”. As you
Properties” section. progress
Here, throughconnections
the logical the diagram, you willthe
between seepreviously
the “Relationships and
defined con-
Properties” section. Here, the logical connections between the previously
cepts are established. A relationship between “Teacher” and “Course” is established defined concepts
are established. A relationship between “Teacher” and “Course” is established through
through the “Taught” property, indicating that a teacher teaches a particular course. In
the “Taught” property, indicating that a teacher teaches a particular course. In the same
the same way, the relationship between “Course” and “Subject” is established through the
way, the relationship between “Course” and “Subject” is established through the “Includes”
“Includes” property, indicating which subjects are covered in a course [20].
property, indicating which subjects are covered in a course [20].

Figure 1. Educational ontology

Figure 1. ontology flowchart.
flowchart.

The
The next
next stage,
stage, “Taxonomic
“Taxonomic Hierarchies”,
Hierarchies”, focuses
focuses on on the
the hierarchical
hierarchical organization
organization ofof
certain
certain concepts. In this case, it shows how the “Subject” class is broken down into
concepts. In this case, it shows how the “Subject” class is broken down into more
more
specific
specific subclasses
subclasses such
such as
as “Math”,
“Math”, “History”,
“History”, andand “Science”,
“Science”, allowing
allowing for for more
more detailed
detailed
categorization.
categorization. “Annotations and Metadata” are a crucial part of ontology design.
“Annotations and Metadata” are a crucial part of ontology design. Here,
Here,
additional
additional definitions
definitions and
and descriptions
descriptions are
are added
added to to each
each concept,
concept, helping
helping to to understand
understand
its
its meaning
meaning and
and context
context in
in the
the educational
educational domain
domain [21].
[21]. For
For example,
example, aa “Student”
“Student” would
would
be
be noted as someone enrolled in an educational institution. The last step of
noted as someone enrolled in an educational institution. The last step of the
the flowchart
flowchart
is “Validation and
is “Validation andRefinement”.
Refinement”.AtAt thisthis stage,
stage, a thorough
a thorough reviewreview
of all of all relationships,
relationships, prop-
properties,
erties, and annotations is performed to ensure consistency and accuracy ofofthe
and annotations is performed to ensure consistency and accuracy theontology.
ontology.
If
If necessary,
necessary,adjustments
adjustmentsarearemade
madetotothe
thetaxonomic
taxonomic hierarchies
hierarchiesto to
reflect thethe
reflect characteristics
characteris-
of the educational domain more accurately.
tics of the educational domain more accurately.
The educational ontology design process was carried out with an innovative approach
to address the unique and changing challenges of today’s educational environment. One of
the key features that differentiated this ontology from others in the field is the dedication
to improving the personalization of learning and knowledge management through an
approach focused on adaptability and interdisciplinarity.
Compared to traditional approaches, this design is based on the understanding that
students and educators face an increasing diversity of learning styles, needs, and prefer-
 Computers 2023, 12, x FOR PEER REVIEW 6 of 20

The educational ontology design process was carried out with an innovative ap-
proach to address the unique and changing challenges of today’s educational environ-
Computers 2023, 12, 199 ment. One of the key features that differentiated this ontology from others in the field is 6 of 19
the dedication to improving the personalization of learning and knowledge management
through an approach focused on adaptability and interdisciplinarity.
Compared
ences. Therefore,to traditional
an ontology approaches, this design
was created is based on
that represents the understanding
static concepts and thatdynamically
students and educators face an increasing diversity of learning styles, needs, and prefer-
adapts to meet individual demands. In addition, properties such as “AdaptiveContent”
ences. Therefore, an ontology was created that represents static concepts and dynamically
were introduced, allowing learning resources to be adjusted according to student’s learning
adapts to meet individual demands. In addition, properties such as “AdaptiveContent”
styles and subject preferences. This unique feature highlights how our ontology adapts to
were introduced, allowing learning resources to be adjusted according to student’s learn-
enhance
ing styles the
andlearning experience in
subject preferences. a personalized
This unique feature and contextualized
highlights how ourway.
ontology
The innovative approach of the proposal is also reflected
adapts to enhance the learning experience in a personalized and contextualized in the representation
way. of
interdisciplinarity in ontology.
The innovative approach While many
of the proposal is alsoprevious
reflected in educational ontologies
the representation of in- focus on
representing isolated
terdisciplinarity concepts,
in ontology. Whilethis
manyontology
previouswas designed ontologies
educational to capturefocus
connections
on rep- between
disciplines.
resenting Theconcepts,
isolated “Interdisciplinary
this ontologyLearning”
was designed class to was introduced
capture connectionsto between
model students’
disciplines. The “Interdisciplinary
ability to explore and relate conceptsLearning”
fromclass wasareas
various introduced to model students’
of knowledge.
abilityFurthermore,
to explore andthe relate conceptsisfrom
ontology various areas
distinguished byofitsknowledge.
hierarchical structure and carefully
Furthermore, the ontology is distinguished
designed relationships. Using properties such as “Taught”by its hierarchical andstructure and carefully
“Includes”, the relationships
designed relationships. Using properties such as “Taught”
between teachers and courses are modeled, as well as the inclusion of and “Includes”, thetopics
relation-
in the study
ships between teachers and courses are modeled, as well as the inclusion of topics in the
plans. These connections provide a complete and coherent view of educational dynamics,
study plans. These connections provide a complete and coherent view of educational dy-
allowing users to explore relationships more deeply and holistically.
namics, allowing users to explore relationships more deeply and holistically.
Figure
Figure 2 represents
2 represents the critical
the critical relationships
relationships betweenbetween three fundamental
three fundamental classes in theclasses in
the educational ontology: “Teacher”, “Course”, and “Subject”.
educational ontology: “Teacher”, “Course”, and “Subject”. These classes and their These classes
inter-and their
interactions are essential to capture the structure of an
actions are essential to capture the structure of an academic environment. academic environment.

Relationships
Figure2.2.Relationships
Figure of the
of the key key concepts
concepts of “Teacher”,
of “Teacher”, “Course”,
“Course”, and “Subject.
and “Subject.

Teacher:
Teacher: This
This class
class represents
represents teachers
teachers who courses
who teach teach courses in the educational
in the educational setting. setting.
Teachers are connected to their systems through the “Teaches” property.
Teachers are connected to their systems through the “Teaches” property. Each teacher may Each teacher may
haveone
have oneorormore
more different
different course
course relationships,
relationships, reflecting
reflecting their to
their ability ability
teach to teach multiple
multiple
subjects.
subjects.
Course:
Course: Courses
Coursesare academic
are academicclassesclasses
offeredoffered
at the educational institution. institution.
at the educational They are They
linked to the teachers who teach them and the subjects they cover. The “Teaches”
are linked to the teachers who teach them and the subjects they cover. The “Teaches” property
connects
propertythe coursesthe
connects to the teachers
courses whoteachers
to the teach them,
whowhile
teachthe “Includes”
them, property
while the estab- property
“Includes”
lishes the relationship with the subjects in the course.
establishes the relationship with the subjects in the course.
Subject: The subjects represent the academic subjects taught in the educational insti-
Subject: The subjects represent the academic subjects taught in the educational insti-
tution. They can be individual subjects or broader categories. They are related to courses
tution. They can be individual subjects or broader categories. They are related to courses
through the “Includes” property, which indicates what topics each class covers.
through the “Includes” property, which indicates what topics each class covers.
The figure shows how teachers (Teachers) are related to the courses they teach (Course)
and how these courses, in turn, include different subjects (Subjects). This representation
of relationships is fundamental for the personalization of learning since it allows a better
adaptation of the courses and issues to the preferences and individual needs of the students.
It also facilitates the efficient management of information in the educational environment,
allowing educators and administrators to make informed decisions about the academic
offer and the assignment of teachers to specific courses.
Comparatively, many traditional educational ontologies and frameworks focus on
isolated concepts, often overlooking the intricate interdisciplinarity present in modern
education. The developed ontology is a pioneer in representing these interdisciplinary
Computers 2023, 12, 199 7 of 19

connections by introducing the “Interdisciplinary Learning” class, which allows students

to explore and unite concepts from various areas of knowledge.
Furthermore, the ontology reduces educators’ time structuring curricular content.
Providing predefined relationships and properties streamlines content organization, en-
suring course consistency and alignment with educational objectives. This contrasts with
previous methodologies that often require laborious structuring of content. This compari-
son highlights the innovative contributions of educational ontology in capturing complex
academic relationships, promoting interdisciplinary learning, and improving knowledge
management.

2.3.2. Development of Educational Ontology

The educational ontology was implemented by OWL, taking advantage of its ability to
define classes, properties, and relationships. This choice was based on its wide adoption and
support in the semantic web community. A semantic mapping process is performed to map
real-world concepts to the ontology. Each idea identified in the design phase was matched to
a class in OWL. For example, the concept “Student” was mapped to the class “Student” and
“Course” to “Course”. Relations are also mapped as properties. The “Teaches” relationship
between “Teacher” and “Course” was converted to the “teachesCourse” property.
The instantiation of classes is done by creating individuals in OWL. Each instance
represented a specific element in the real world. For example, “Student” and “Course”
were instantiated to represent actual students and courses. These instances are linked using
properties to establish relationships [22]. For example, a “Student” individual was linked
to a “Course” individual using the “enrolled” property.
The binding of properties and relationships is achieved using axioms in OWL. Where
premises are defined to establish connections between classes and individuals. For example,
assumptions are used to state that if a student is enrolled in a course, then the student is part
of the class “Student”, and the system is part of the class “Course”. This implementation
process allowed the construction of a coherent and semantically rich educational ontology.
The resulting ontology is validated by reasoning tests and queries to ensure correct inference
Computers 2023, 12, x FOR PEER REVIEW
and consistency. 8 of 20
The mapping in Figure 3 describes how real-world concepts are represented in the
educational ontology using the OWL language.

Figure 3.
Figure Educational ontology
3. Educational ontology in
in OWL,
OWL, including
including more
more classes,
classes, properties,
properties, and
and individuals.
individuals.

The figure details the components:

Classes
• Student: Represents the students. Students can be enrolled in courses and take tests.
Computers 2023, 12, 199 8 of 19

The figure details the components:

Classes
• Student: Represents the students. Students can be enrolled in courses and take tests.
The “Student” class is used in the ontology.
• Professor: Represents the teachers. Professors can teach courses and belong to a
department. The “Professor” class is used in the ontology.
• Course: Represents a course taught at the university. Systems may have lectures,
homework, and exams. The “Course” class is used in the ontology.
• Lecture: Represents a lecture or class delivered as a course. Conferences can have
associated assignments. The “Lecture” class is used in the ontology.
• Assignment: Represents a task or assignment given to students as part of a course.
The “Assignment” class is used in the ontology.
• Exam: Represents an exam given as part of a course. Exams can belong to a department.
The “Exam” class is used in the ontology.
• Department: Represents a department within a university. Departments can have
associated courses and professors. The “Department” class is used in the ontology.
• University: Represents a university. Universities may have departments and courses.
The “University” class is used in the ontology.
Properties
• enrolledIn: A property that connects a student to their enrolled courses.
• teachesCourse: A property that connects a teacher to her courses.
• hasLecture (has lecture): A property that connects a course with its component lectures.
• hasAssignment: A property that connects a conference with the associated assign-
ments.
• takesExam: A property that connects a student to the tests she has taken.
• belongsToDepartment (belongs to department): A property that connects a course,
teacher, or exam with the department to which it belongs.
• worksAt (works at): A property that connects a professor to the university where he
works.
Individuals (instances)
• Individual instances are created to represent students, teachers, courses, lectures,
assignments, tests, departments, and universities. Each model is related to the corre-
sponding classes and properties according to its role in the educational context.
The mapping allows a complete semantic representation of educational concepts and
their relationships in the ontology domain [23]. Each class and property defined in the
ontology aims to capture the essential details of the interactions and structures in the
educational environment.

2.3.3. Data Acquisition

Data acquisition was done through a combination of information sources covering
various educational environment aspects. Online academic repositories, university web-
sites, and specialized education databases are used. These sources provide access to course
descriptions, syllabi, faculty and student details, and course materials. The data extraction
methodology involves web scraping techniques and text processing to obtain structured
and semi-structured information [24]. Custom scripts were implemented to access relevant
web pages and extract critical data such as course names, descriptions, lecture dates, as-
signment details, and exam results. The data obtained is transformed into a suitable format
for subsequent incorporation into the ontology.
The quality and integrity of the data collected are fundamental aspects of the acquisi-
tion process. These measures were implemented to guarantee the accuracy and reliability
of the extracted data. This includes cross-validation of extracted information with multiple
sources, cleaning inconsistent data, and eliminating duplicates. In addition, a manual
verification process is carried out to ensure that the data accurately reflects the reality of
Computers 2023, 12, 199 9 of 19

the educational environment [25]. Once the data are extracted and validated, we integrate
it into the educational ontology. For this, specific tools and languages are used to map the
collected data into the classes and properties defined in the ontology. Individual instances,
such as students, teachers, courses, and assignments, are created and related based on
corresponding classes and properties. This allows for enriching the ontology with relevant
and coherent information [26].

2.3.4. Validation and Verification

The validation of the ontology is carried out through the collaboration of experts in
the educational domain. A review committee of professionals with experience in education,
pedagogy, and information technology was established [27]. These experts reviewed
the ontology in detail and provided feedback on the accuracy and appropriateness of
the defined concepts, relationships, and properties. Your comments and suggestions are
considered for adjustments and improvements to the ontology. In addition, validation
is carried out based on specific use cases. Real educational scenarios are selected, and
the results from the ontology are compared with the corresponding information in the
real world. This makes it possible to assess the ontology’s ability to represent educational
knowledge accurately and coherently.
To guarantee its validity, consistency and coherence tests are carried out in the on-
tology to ensure no contradictions or ambiguities in the definitions and relationships
established [28]. Ontological reasoners were implemented that verified the logic and coher-
ence of the inferences made in the ontology. Any identified inconsistencies are corrected
and validated by domain experts. The relevance of the ontology is evaluated through
comparison with other existing educational ontologies and feedback from end users [29]. It
analyzes how the ontology captures specific concepts and relationships compared to other
ontological resources.
The validation results indicate that the developed ontology could wholly and accu-
rately capture the desired educational knowledge. The consistency and coherence tests
show that the ontology does not present contradictions or ambiguities in its structure.
The relevance assessment reveals that the ontology provided a robust framework for
representing and organizing educational knowledge.

2.3.5. Practical Implementation

The educational ontology was integrated into an online learning platform used by
students and educators from the university participating in the study. A specific module
was developed to achieve this, allowing interaction with the ontology. Users can access
the ontology through an intuitive interface to explore the concepts, relationships, and
properties defined in the ontology.
The ontology is used to personalize the learning experience of students. By analyzing
students’ profiles and learning preferences, the ontology identified relevant educational
resources and suggested activities according to their needs. This allows students to access
specific content adapted to their learning styles, thus improving their engagement and
academic performance. The ontology is crucial in enhancing the search for information
within the educational platform. Students and educators use ontology-based queries to
search for resources related to specific concepts. The ontology enriches the investigation by
providing more relevant and contextual results, facilitating the location of study materials
and complementary resources.
In addition, this tool was used to facilitate knowledge management in the educational
platform. Educators can create and organize curricular content using the concepts and
relationships of ontology [30]. This allows a more efficient structuring of the content and the
creation of coherent learning paths aligned with the educational objectives. In addition, the
ontology makes it possible to identify gaps in the content and generate recommendations
to improve the thematic coverage.
Computers 2023, 12, 199 10 of 19

The practical implementation of ontology in the educational environment has proven

successful. Students experienced a more personalized and enriching learning experience,
translating into greater interest and engagement with the educational material. Improving
the search for information allows users to access the necessary resources, optimizing their
study time [31]. In addition, ontology-based knowledge management helps educators
design more structured courses that align with educational objectives.
Although our primary focus is ontology, complementary pedagogical approaches can
be considered in an implementation, such as concept map-based education. Education
based on concept maps is based on the visual representation of concepts and relationships,
which facilitates the understanding and organization of knowledge [32]. The ontology
designed to personalize the learning experience can collaborate with idea map-based
approaches to further improve the quality of personalized education.
One of the ways to integrate ontology with concept map-based education is by creat-
ing personalized concept maps for students. By using ontology to understand students’
preferences and learning objectives, it is possible to adapt the construction of concept maps
so that they more accurately reflect the individual needs of each student. This could lead to
a more meaningful and effective learning experience. Another potential integration point
lies in the promotion of metacognition and self-regulation of learning. Concept maps help
students visualize concepts and encourage reflection on how those concepts are related [33].
Using the ontology to track learning progress and interactions with resources could provide
students with a valuable tool to self-regulate their learning. This could improve autonomy
and learning effectiveness.

2.3.6. Evaluation and Results

To assess the effectiveness of the ontology in the educational environment, key metrics
are defined that address different aspects of the student experience and the usefulness of
the ontology. These metrics include:
• Improvement in the Student Experience: A survey is used for students who use the
platform with the integrated ontology to measure their perception of the personaliza-
tion of the learning experience. The questions address the relevance of the suggested
resources, the adaptation to your learning styles, and the impact on your academic
engagement.
• Accuracy in Information Retrieval: the accuracy of the search results when using
queries based on the ontology is evaluated. The results obtained using the ontology
are compared with those obtained using traditional search methods.
• Efficiency in Knowledge Management: Educators’ creation and organization of cur-
ricular content using ontology is analyzed. The reduction in the time dedicated to
structuring the content and the coherence of the designed courses are measured.
The results of the evaluation demonstrate significant improvements in several key
aspects:
• The student survey revealed that 82% of respondents perceived an improvement in
the personalization of their learning experience. Students expressed that the suggested
resources aligned more with their interests and learning styles.
• Information retrieval accuracy increased by 25% when using ontology-based queries
compared to traditional search methods. Results were more relevant and contextual,
making it easier for students to locate specific resources.
• Educators experienced a 30% reduction in time spent creating and organizing curricu-
lar content. The ontology provided a predefined structure that streamlined the process
and ensured course consistency.
The results support the educational ontology’s effectiveness and usefulness in the
academic environment. The personalization of the learning experience was significantly im-
proved, resulting in higher student engagement and satisfaction. Accuracy in information
retrieval is markedly enhanced, benefiting students and educators by accessing relevant
Computers 2023, 12, 199 11 of 19

resources efficiently. Knowledge management also experienced substantial improvements

in terms of efficiency and coherence.

3. Results
The consideration of various use cases and scenarios in the educational environment is
the basis of the design of this ontology. We recognize that education spans different contexts
and needs, from traditional classrooms to online learning environments and from primary
to higher education. Therefore, this design strove to ensure the relevance and applicability
of the concepts and relationships captured in the ontology in various educational situations.
We collaborated with educators, students, and administrators at different educational
levels to address this consideration. Surveys and interviews were conducted to understand
their specific needs and how they relate to the use of ontology. This direct feedback makes
it possible to adjust and refine the concepts and properties in the ontology to make them as
relevant and valuable as possible.
A concrete example of how this consideration is addressed is through the “Educa-
tionalLevel” property, which allows you to classify concepts and resources according to
the educational level to which they apply, such as primary, secondary, or university. This
ensures that users can access information and resources relevant to their level of education,
which is essential to personalize the learning experience. Furthermore, when designing
relationships such as “Taught” between teachers and courses, we considered how these
interactions might vary in different educational levels and settings.
In terms of specific users, the design was focused on their unique needs and goals. For
students, properties such as “LearningStyle” and “PreferredSubjects” are created, allowing
them to receive recommendations for learning resources and activities that align with
their preferences and learning styles. For educators, the “TeachingApproach” property is
introduced, which allows them to customize teaching strategies according to the needs and
characteristics of students.

3.1. Deployment Environment Description

The educational ontology was implemented and evaluated in the academic environ-
ment of the institution participating in the study, specifically in an online learning platform
widely used. This digital platform provides students and educators with a comprehensive
virtual space for course management, educational resources, and interactive activities. The
selection of this platform was based on its popularity and ability to incorporate innovative
technologies to enhance the educational experience effectively.
The initial pilot of the ontology implementation involved 350 students and 12 educa-
tors from various academic disciplines, such as engineering, social sciences, and humanities.
This diversity of academic areas allowed us to evaluate the usefulness and applicability of
ontology in different educational contexts. The students represented a mix of educational
levels, from introductory courses to more advanced levels, providing a holistic view of how
ontology could benefit a wide range of users. The participating teachers have experience
in both face-to-face and online teaching, which enriched the collaboration in adapting
curricular contents and activities to the conceptual structure of the ontology. This close col-
laboration between the ontology development team and the educators ensured consistent
and efficient ontology integration into the educational environment.
The ontology was implemented in the online learning platform through specific
tools and functionalities. These included features such as enhanced semantic search,
recommendation of educational resources based on user profiles, and visualization of
conceptual relationships between study topics. Students accessed these functionalities as
they explored their course content and engaged in learning activities. The implementation
of the ontology was developed in several stages, beginning with the adaptation of the
ontology structure to the university’s educational objectives. Then, we created instances of
classes and properties in the ontology, mapping real-world concepts to ontological elements.
Computers 2023, 12, 199 12 of 19

Class instances were generated from course materials, and relationships were established
between them to reflect conceptual interconnections.

3.2. Study Population

The study population that participated in implementing and evaluating the educa-
tional ontology comprised 350 students from various academic fields and educational levels.
In terms of age distribution, most students are between the ages of 18 and 25, which corre-
sponds to the typical student population of the university. Equal gender representation
was considered, with an approximate split of 55% female and 45% male students.
Regarding the educational level, the study population covers a wide range of courses
and classes. Students from early undergraduate years to advanced students in graduate
programs were included. This allows for the evaluation of how the ontology can be adapted
to different levels of curricular complexity and pedagogical approaches. Additionally,
information was collected on the students’ fields of study. These fields spanned engineering,
social sciences, humanities, natural sciences, and more. Each area has its specific learning
requirements and curricular objectives, which provide a unique opportunity to assess the
applicability of the ontology in diverse educational contexts.
Within the framework of the study, control groups were implemented to make mean-
ingful comparisons. One group of students used the online learning platform without
incorporating the ontology, while another group had access to the enhanced functionalities
enabled by the ontology. This configuration allowed us to effectively evaluate the specific
impacts and benefits of the ontology to the learning experience and knowledge manage-
ment. The collection of demographic data and the implementation of control groups
contributed to obtaining a complete and representative understanding of how the ontology
influenced the learning and interaction of students in the educational environment. In the
following sections, the quantitative and qualitative results obtained through this study will
be presented, supported by detailed analyses of the data collected.

3.3. Specific Use Cases

One of the most prominent use cases was the personalization of the learning experience
for each student. The ontology allowed the creation of student profiles based on their
interests, preferences, and learning objectives. Analyzing these profiles, the ontology
recommended specific instructional resources, activities, and assessments aligned with
each student’s needs. This resulted in a more relevant and engaging learning experience,
as students felt empowered to explore content that interested them. Another essential use
case is the improvement of information search. The ontology allows precise categorization
and labeling of educational resources, facilitating the retrieval of relevant information.
Students can use more precise queries and receive more relevant and specific results. This
streamlined the research process and allowed students to quickly access relevant content
for their assignments and projects.
The ontology also proved to be a valuable tool for efficient knowledge management.
Educators could organize and structure their course content more coherently using ontology
as a guide. In addition, the ontology makes it easy to identify gaps in knowledge and areas
where students might need additional support. This allows educators to make informed
decisions to optimize curriculum design and adapt teaching strategies based on the actual
needs of students. A concrete example of the successful application of ontology is the
personalization of learning resources for an engineering course. Students can specify
their interests in areas such as artificial intelligence and robotics. The ontology used this
information to identify and recommend course modules, readings, tutorials, and projects
directly related to the stated interests. As a result, students feel more engaged with the
course content, resulting in increased engagement and academic performance.
The specific use cases demonstrate the versatility and impact of educational ontology
in the academic environment. Personalizing the learning experience, enhancing information
search, and facilitating knowledge management offer significant opportunities to enrich
Computers 2023, 12, 199 13 of 19

education and empower learners and educators. These use cases highlight the potential
of ontology as a powerful tool to address educational challenges and transform how
knowledge is accessed and harnessed in academia. The following section will analyze the
results and conclusions from implementing and evaluating the educational ontology.

3.4. Technical Implementation in the Learning Management System and Online Platforms
Implementing the educational ontology in the academic environment is carried out
thoroughly and strategically to ensure an effective integration that will benefit students
and educators. For this, Moodle was chosen as the LMS for implementation due to its
broad adoption in educational institutions and ability to adapt to diverse educational
environments.

3.4.1. Moodle Configuration for RDF

The first stage in the implementation was to configure Moodle to accept data in
the resource description framework (RDF) format, which is essential to represent the
educational ontology semantically. This choice is based on RDF’s ability to accurately
express semantic relationships and its compatibility with semantic web standards. In
this configuration, data structures are defined in Moodle so that they can host semantic
information. This involves the creation of specific fields and metadata in Moodle that
would allow the assignment of ontological concepts. Every element in Moodle related to
the ontology, such as courses, activities, and users, was configured to store and process RDF
data. This approach ensures a solid foundation for semantically representing the ontology
and its relationships within the LMS.

3.4.2. Mapping of Classes and Ontological Properties

A critical step in the implementation is mapping ontological classes to specific elements
in Moodle. This was done to establish coherent semantic relationships between the different
components of the system. For example, the ontological class “Course” was mapped to
the Moodle course structure, allowing alignment of the ontology with the actual courses
offered on the platform. Precise ontological relationships are defined to connect elements
in Moodle with ontological concepts. For example, it establishes how users (students
and educators) relate to the courses they take or teach. This allows for a full semantic
representation of the interactions between users and systems in Moodle.

3.4.3. Creation of Examples and Ontological Relationships

To implement, specific examples of ontological classes are created within Moodle.
These examples are based on the corresponding ontological types and represent concrete
instances of educational concepts. This includes creating systems, learning activities, user
profiles, and other elements based on complementary ontological concepts. Ontological
relationships were configured between the instances created in Moodle. For example,
connections are established between teachers (representatives of the ontological class
“Teacher”) and the courses they taught (instances of the ontological class “Course”). This
ensures that the relationships between elements in Moodle closely reflect the underlying
ontological relationships.

3.4.4. Advanced Semantic Search and Personalized Recommendations

The implementation included an advanced semantic search function that took advan-
tage of the ontological structure. This improved the accuracy and relevance of search results
by considering the semantics of concepts rather than simply keywords. The recommenda-
tion algorithms are based on the ontological profiles of the users in Moodle. This allows
students to receive personalized recommendations for learning resources and activities
based on their ontological profiles, such as preferences and learning goals.
Computers 2023, 12, 199 14 of 19

3.4.5. Visualization of Ontological Relationships

A visualization function is incorporated into Moodle to improve understanding of
the interconnections between different topics and concepts. This allows users to visually
explore the ontological relationships between concepts within courses and resources. This
visualization feature makes it easy to understand how the pictures are related to each other
and how they are integrated into the course content.

3.4.6. User Interaction in Moodle

The implementation allows students to interact with the ontology in Moodle mean-
ingfully. Students could customize their learning experiences based on their preferences,
goals, and learning styles. They received specific recommendations and were able to adapt
their learning path based on their ontological profiles. Educators also used the ontology as
a guide to structure courses and understand student needs. This allowed them to make
informed decisions about adapting content and teaching strategies.

3.4.7. Implementation Benefits

This implementation ensured a strong integration of ontology into the digital educa-
tional environment, significantly improving the personalization of learning and knowledge
management. Students experienced learning more tailored to their needs, leading to greater
engagement and better academic performance. Educators benefited from a better under-
standing of students’ preferences and needs, allowing them to deliver more effective and
personalized instruction.

3.5. Quantitative and Qualitative Results

The results fall into two main categories: the impact on the learning experience and
the effectiveness of knowledge management.

3.5.1. Impact on the Learning Experience

Surveys and questionnaires were carried out to assess students’ perceptions of how
the ontology affected their learning experience. The results are summarized in Table 1.

Table 1. Impact on the learning experience.

Aspect Percentage of Satisfied Students

Personalization of Learning 82%
Information Search Improvement 75%
Diversity of Resources 68%

Students who used the ontology reported a more personalized and goal-oriented learn-
ing experience. Most students highlighted the improvement in the search for information
and the variety of resources available.

3.5.2. Effectiveness in Knowledge Management

The ontology also proved effective in knowledge management and organization, as
shown in Table 2.

Table 2. Enhancing the learning experience: student satisfaction percentages.

Aspect Percentage of Satisfied Students

Access to Interdisciplinary Knowledge 60%
Progress Tracking 72%

The ontology allowed students to explore relationships between seemingly unrelated

areas of knowledge and receive personalized guidance for their learning. Educators
appreciated the ability to track individual student progress.
Computers 2023, 12, 199 15 of 19

3.5.3. Qualitative Analysis

In addition to the surveys, in-depth interviews are conducted with a subset of students
and educators. The comments of the participants are summarized in Table 3.

Table 3. Participant feedback: impact of the ontology on learning and teaching experience.

Participant Comment
Student 1 “The ontology helped me find specific resources for my research project”.
Student 2 “Exploring the connections between different disciplines enriched my perspective”.
Educator 1 “I was able to personalize the learning activities based on each student’s progress”.
Educator 2 “Ontology fostered more informed and enriching discussions in class”.

Feedback highlights the usefulness of the ontology for personalized resource search,
interdisciplinary exploration, and enhancing classroom interaction.

3.6. Comparison with Other Methods

An exhaustive comparison was made between the implementation of the educational
ontology and traditional methods or previous systems that did not take advantage of the
ontology for knowledge management in the academic environment. The objective is to
highlight the benefits and improvements the ontology provides regarding effectiveness,
efficiency, and user experience. Before ontology implementation, the educational environ-
ment relied heavily on traditional knowledge management methods, such as manually
searching libraries and databases, organizing physical files, and directly interacting with
educators to access resources. These approaches have significant limitations regarding
accessibility, constant updating of content, and personalization of the learning experience.
The ontology demonstrated a significant improvement in knowledge management
efficiency compared to traditional methods. Students reported that they could access
relevant resources more quickly and accurately, resulting in substantial time savings when
conducting research and learning activities. In addition, the hierarchical structure of
the ontology facilitated navigation and interdisciplinary exploration, which contributed
to a deeper understanding of the concepts. The ontology also proved more effective
in organizing and presenting educational content. Traditional methods could not often
establish relationships and connections between different areas of knowledge. In contrast,
ontology allowed students to discover previously unidentified relationships between
concepts, which enriched their learning and fostered a more holistic understanding.
Regarding user experience, ontology outperformed traditional methods by providing a
more personalized and adaptable learning experience. Students could define their interests
and learning goals, which led to recommendations for specific resources and relevant
activities. This ability to personalize increased students’ motivation and engagement with
the learning process.

4. Discussion
Implementing educational ontology in an academic environment yielded promising
results supporting its effectiveness and usefulness. The data collected during the study
revealed that using the ontology led to significant improvements in the personalization
of the learning experience, efficiency in information search, and knowledge management.
Regarding personalization, students who used the ontology reported higher satisfaction
with course content and higher motivation to explore areas of personal interest [34]. This
suggests that the ontology successfully tailors educational content to individual student
preferences, positively influencing their engagement and academic performance.
The ontology also demonstrated its ability to improve the search for information.
Students who used the ontology found the resources relevant to their assignments and
projects faster, which streamlined the research process and contributed to the submitted
papers’ quality [35]. In addition, teachers highlighted how ontology facilitated knowledge
Computers 2023, 12, 199 16 of 19

management by providing a coherent structure for organizing and presenting course

content. This made it possible to identify areas for improvement in the study plan and
adjust teaching strategies based on the detected needs.
Compared to previously reviewed work in knowledge representation and ontology-
based data management, our approach stands out for its focus on education and its impact
on the learning experience. While many previous results focused on specific applications,
such as enterprise data management or knowledge representation in medicine, our edu-
cational ontology spans a broader spectrum of academic disciplines and aims to improve
education.
In terms of effectiveness and efficiency, our results show similarities with previous
works that applied ontologies to personalize the user experience and improve information
retrieval. For example, the work [36] used an ontology to recommend personalized educa-
tional resources to university students. While our approaches are similar, our educational
ontology addresses a broader range of use cases, including knowledge management and
improving the learning experience [37].
The successful implementation of educational ontology suggests several practical and
theoretical educational implications. From a practical perspective, our ontology offers an
innovative solution to address common academic challenges, such as lack of customization
and difficulty in knowledge management [38]. The ability to tailor educational content to
individual student needs and preferences can significantly contribute to student retention
and academic achievement.
In addition, the educational ontology can serve as the basis for future research and
development in technology-assisted education [39]. For example, integrating artificial
intelligence technologies and data analysis can further enhance the personalization of
the learning experience and improve educational decision-making. Furthermore, the
ontology could be extended to address specific challenges, such as formative assessment
and content adaptation for students with special needs. In theoretical terms, our research
contributes to the growing understanding of how ontologies can transform education and
improve the student experience. By highlighting the importance of accurate and structured
knowledge representation in education, our educational ontology highlights the need for
interdisciplinary approaches that combine information technology with pedagogy and
educational psychology.
The essence of the design of this educational ontology lies in its ability to enrich the
personalization of learning, allowing a more precise adaptation of educational resources to
the individual needs and preferences of students. One of the crucial aspects in this regard
is the “LearningStyle”. By capturing each student’s preferred learning style, our ontology
can recommend resources and activities that align with their cognitive preferences, thus
optimizing their engagement and understanding in the learning process. For example,
suppose a student demonstrates a visual learning style. The ontology might suggest
resources with more prominent optical components, such as graphics and videos, to
maximize their retention and comprehension.
The “EducationalLevel” property also plays a crucial role in personalizing learning.
By categorizing resources and activities according to the educational level of the students,
the ontology ensures that users access content appropriate for their level of knowledge.
For example, a beginner-level student might receive recommended activities to reinforce
fundamental concepts, while a more advanced student might receive suggestions for
exploring more complex and challenging topics. This adaptation based on educational
level optimizes the relevance and relevance of the materials presented, enhancing the
academic experience.
In addition, the “Interest” property further amplifies the personalization of learning.
By capturing students’ individual interests, the ontology can identify areas of greatest
attraction and motivation for each one. For example, if a student is interested in marine
biology, the ontology could recommend resources and projects related to this field, fostering
greater immersion and engagement in learning.
Computers 2023, 12, 199 17 of 19

Through these design features, this ontology significantly impacts the personalization
of learning. Understanding and addressing students’ cognitive preferences, educational
levels, and areas of interest, ontology becomes a powerful tool for delivering an enrich-
ing and individualized learning experience. The precise adaptation of the resources and
activities improves the comprehension and retention of the contents and fosters a tremen-
dous enthusiasm and commitment to the educational process. Ultimately, ontology design
creates a more satisfying and practical learning experience for each student.

5. Conclusions
The implementation and evaluation of the educational ontology in an academic envi-
ronment has given us a revealing vision of its transformative potential in contemporary
education. Through this study, we have provided a comprehensive and practical approach
to address critical educational challenges, such as personalizing the learning experience,
improving information search, and knowledge management. Our results support the idea
that ontologies can play a fundamental role in improving the efficiency and effectiveness
of educational processes, establishing a new horizon for education based on semantic
technologies.
One of the most notable conclusions of this study is the ability of educational ontology
to personalize students’ learning experiences. Tailoring educational content to individual
student preferences and needs has significantly impacted their engagement and academic
performance. Our ontology has proven to be an effective tool for delivering a more
student-centered education, which could contribute to higher student retention and more
substantial educational outcomes.
In addition, educational ontology has proven to be a valuable tool to improve the
efficiency of information search and knowledge management. The ability to organize and
present educational content in a structured and coherent manner has made it easier for
students and educators alike to find and access the resources needed for their academic pur-
suits. This translates into greater productivity in research and more informed educational
decision-making.
By comparing our results with previous work in knowledge representation and
ontology-based data management, we can highlight the breadth and versatility of our
educational ontology. While many previous works focused on specific applications, such as
business management or healthcare, our ontology covers various disciplines and use cases
in the educational context. This further reinforces the idea that ontologies can be powerful
and adaptable tools in multiple domains.
However, we recognize limitations and areas for improvement in our study. While the
results are promising, it is essential to note that the implementation and evaluation were
carried out in a specific setting and with a population of individual learners and educators.
The scalability and generalization of our ontology to different educational contexts may
require additional adjustments and adaptations. In addition, integrating emerging tech-
nologies, such as artificial intelligence and data analytics, could offer other opportunities
further to improve the personalization and efficiency of ontology-based education.
Looking to the future, it is essential to recognize the need to continue advancing this
line of research. Additional future work that expands and strengthens our educational
ontology would be valuable. These works could include adapting the ontology to different
educational contexts, exploring new emerging technologies such as artificial intelligence
and data analytics, and collaborating with various educational institutions to further
evaluate its effectiveness in multiple settings. Furthermore, it is essential to explore how
our ontology can contribute to the continued evolution of education in the digital age.
These additional research efforts will contribute to the development of a continuously
improving educational ontology and its application in modern education.
Computers 2023, 12, 199 18 of 19

Author Contributions: Conceptualization, W.V.-C.; methodology, W.V.-C.; software, J.G.-O.; vali-

dation, J.G.-O.; formal analysis, W.V.-C.; investigation, J.G.-O.; data curation, W.V.-C. and J.G.-O.;
writing—original draft preparation, J.G.-O.; writing—review and editing, J.G.-O.; visualization,
W.V.-C.; supervision, W.V.-C. All authors have read and agreed to the published version of the
manuscript.
Funding: This research received no external funding.
Data Availability Statement: Not applicable.
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Capuano, N.; Mangione, G.R.; Pierri, A.; Salerno, S. Personalization and Contextualization of Learning Experiences Based on
Semantics. Int. J. Emerg. Technol. Learn. 2014, 9, 5. [CrossRef]
2. Mylonas, P. A Fuzzy Contextual Approach towards Intelligent Educational Content Adaptation. In Proceedings of the SMAP07—
Second International Workshop on Semantic Media Adaptation and Personalization, Uxbridge, UK, 17–18 December 2007.
3. Romero, L.; Gutierrez, M.; Caliusco, M.L. Conceptual Modeling of Learning Paths Based on Portfolios: Strategies for Selecting
Educational Resources. In Proceedings of the Iberian Conference on Information Systems and Technologies (CISTI), Caceres,
Spain, 13–16 June 2018.
4. Daǧ, F.; Erkan, K. A Personalized Learning System Based on Semantic Web Technologies. In Intelligent Tutoring Systems in
E-Learning Environments: Design, Implementation and Evaluation; Stankov, S., Glavinic, V., Rosic, M., Eds.; IGI Global: Hershey, PA,
USA, 2010.
5. Silva-Lopez, R.B.; Sanchez-Arias, V.G.; Mendez-Gurrola, I.I. Ontological Model to Represent the Student’s Learning Profile.
In Proceedings of the 6th International Conference of Education, Research and Innovation (ICERI 2013), Seville, Spain, 18–20
November 2013.
6. Rtili, M.K.; Khaldi, M.; Dahmani, A. Modeling Approach to Learner Based Ontologies for the Recommendation of Resources in
an Interactive Learning Environments. J. Emerg. Technol. Web Intell. 2014, 6, 340–347.
7. Băjenaru, L.; Smeureanu, I. Learning Style in Ontology-Based E-Learning System. In Proceedings of the International Conference
on Informatics in Economy, Cluj-Napoca, Romania, 2–3 June 2018; Volume 273.
8. Machado, J.B.; Martins, G.L.; Isotani, S.; Barbosa, E.F. An Ontology-Based User Model for Personalization of Educational Content.
In Proceedings of the International Conference on Software Engineering and Knowledge Engineering (SEKE), Boston, MA, USA,
27–29 June 2013.
9. Zhu, Y.; Zhang, W.; He, Y.; Wen, J.; Li, M. Design and Implementation of Curriculum Knowledge Ontology-Driven SPOC Flipped
Classroom Teaching Model. Kuram Uygulamada Egit. Bilim. 2018, 18, 1351–1374. [CrossRef]
10. Costa, L.A.; Pereira Sanches, L.M.; Rocha Amorim, R.J.; Salvador, L.D.N.; dos Santos Souza, M.V. Monitoring Academic
Performance Based on Learning Analytics and Ontology: A Systematic Review. Inform. Educ. 2020, 19, 361–397. [CrossRef]
11. Sami, B.; Yasin, H.; Mohammad Yasin, M. Automated Score Evaluation of Unstructured Text Using Ontology. Int. J. Comput. Appl.
2012, 39, 19–22. [CrossRef]
12. Engel, A.; Coll, C. Hybrid Teaching and Learning Environments to Promote Personalized Learning. RIED-Rev. Iberoam. Educ. A
Distanc. 2022, 25, 225–242. [CrossRef]
13. Carbonaro, A. Concept Integration to Develop Next Generation of Technology-Enhanced Learning Systems. In Project and Design
Literacy as Cornerstones of Smart Education, Proceedings of the Smart Innovation, Systems and Technologies, 27 September 2019; Rehm,
M., Saldien, J., Manca, S., Eds.; Springer: Singapore, 2020; Volume 158, pp. 121–129.
14. Blanco-Fernández, Y.; Pazos-Arias, J.J.; Gil-Solla, A.; Ramos-Cabrer, M.; López-Nores, M.; García-Duque, J.; Fernández-Vilas,
A.; Díaz-Redondo, R.P.; Bermejo-Muñoz, J. A Flexible Semantic Inference Methodology to Reason about User Preferences in
Knowledge-Based Recommender Systems. Knowl. Based Syst. 2008, 21, 305–320. [CrossRef]
15. Labib, A.E.; Canos, J.H.; Penades, M.C. Integrating Product Line and Learning Style Approaches to Enforce Reusability and
Personalization of Learning Objects. In Proceedings of the IEEE 17th International Conference on Advanced Learning Technologies
(ICALT), Timisoara, Romania, 3–7 July 2017.
16. Terzieva, V.; Ivanova, T.; Todorova, K. Personalized Learning in an Intelligent Educational System. In Novel & Intelligent
Digital Systems: Proceedings of the 2nd International Conference (NiDS 2022); Krouska, A., Troussas, C., Caro, J., Eds.; Springer:
Berlin/Heidelberg, Germany, 2023.
17. Yessad, A.; Faron-Zucker, C.; Laskri, M.T. Ontology-Based Personalization of Hypermedia Courses. Int. Rev. Comput. Softw. 2008,
3, 1–28.
18. Wang, H.C.; Huang, T.H. Personalized E-Learning Environment for Bioinformatics. Interact. Learn. Environ. 2013, 21, 18–38.
[CrossRef]
19. Pham, Q.D.; Adina, M.F. Adaptation to Learners’ Learning Styles in a Multi-Agent E-Learning System. Internet Learn. 2013, 2,
11–20. [CrossRef]
Computers 2023, 12, 199 19 of 19

20. Siino, M.; La Cascia, M.; Tinnirello, I. WhoSNext: Recommending Twitter Users to Follow Using a Spreading Activation Network
Based Approach. In Proceedings of the IEEE International Conference on Data Mining Workshops (ICDMW), Sorrento, Italy,
17–20 November 2020.
21. Guan, Y.; Wei, Q.; Chen, G. Deep Learning Based Personalized Recommendation with Multi-View Information Integration. Decis.
Support Syst. 2019, 118, 58–69. [CrossRef]
22. Behera, R.K.; Gunasekaran, A.; Gupta, S.; Kamboj, S.; Bala, P.K. Personalized Digital Marketing Recommender Engine. J. Retail.
Consum. Serv. 2020, 53, 101799. [CrossRef]
23. Castro, F.; Alonso, M.A. Learning Objects and Ontologies to Perform Educational Data Mining. In Proceedings of the 2011
International Conference on Frontiers in Education: Computer Science and Computer Engineering (FECS’11), Las Vegas, NE,
USA, 18–21 July 2011.
24. Iatrellis, O.; Kameas, A.; Fitsilis, P. An Ontological Approach for Semantic Modeling of Learning Pathways. In Proceedings of
the 2017 IEEE 26th International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE),
Poznan, Poland, 21–23 June 2017.
25. Iatrellis, O.; Kameas, A.; Fitsilis, P. Educ8: Self-Evolving and Personalized Learning Pathways Utilizing Semantics. In Proceedings
of the 2018 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS), Rhodes, Greece, 25–27 May 2018.
26. Sharma, S.; Shakya, H.K.; Marriboyina, V. A Location Based Novel Recommender Framework of User Interest through Data
Categorization. Mater. Today Proc. 2021, 47, 7155–7161. [CrossRef]
27. Iatrellis, O.; Kameas, A.; Fitsilis, P. Personalized Learning Pathways Using Semantic Web Rules. In Proceedings of the 21st
Pan-Hellenic Conference on Informatics, Larissa, Greece, 28–30 September 2017.
28. Adorni, G.; Battigelli, S.; Brondo, D.; Capuano, N.; Coccoli, M.; Miranda, S.; Orciuoli, F.; Stanganelli, L.; Sugliano, A.M.; Vivanet,
G. CADDIE and IWT: Two Different Ontology-Based Approaches to Anytime, Anywhere and Anybody Learning. J. E-Learn.
Knowl. Soc. 2010, 6, 53–66.
29. Kovatcheva, E.; Nikolov, R. An Adaptive Feedback Approach for E-Learning Systems. IEEE Multidiscip. Eng. Educ. Mag. 2009,
4, 1–3.
30. Kerkiri, T.; Manitsaris, A.; Mavridis, I. How E-Learning Systems May Benefit from Ontologies and Recommendation Methods to
Efficiently Personalise Resources. Int. J. Knowl. Learn. 2009, 5, 347–370. [CrossRef]
31. Amine Alimam, M.; Seghiouer, H. Personalized E-Learning Environment Based on Ontology to Improve Students’ School Levels.
Int. J. Comput. Appl. 2013, 84, 1–12. [CrossRef]
32. Sharif Ullah, A.M.M. W-12 Manufacturing Engineering Courses and Web-Based Education. JSEE Annu. Conf. Int. Sess. Proc. 2013,
2013, 72–77. [CrossRef]
33. Ullah, A.S. What Is Knowledge in Industry 4.0? Eng. Rep. 2020, 2, e12217. [CrossRef]
34. Hsu, T.Y.; Ke, H.R.; Yang, W.P. Knowledge-Based Mobile Learning Framework for Museums. Electron. Libr. 2006, 24, 635–648.
[CrossRef]
35. Ivanova, T.; Terzieva, V.; Ivanova, M. Intelligent Technologies in E-Learning: Personalization and Interoperability. In Proceedings
of the 22nd International Conference on Computer Systems and Technologies, New York, NY, USA, 18–19 June 2021.
36. Taurus, J.; Niu, Z.; Khadidja, B. E-Learning Recommender System Based on Collaborative Filtering and Ontology. Int. J. Comput.
Inf. Eng. 2017, 11, 256–261.
37. Bajenaru, L.; Smeureanu, I. An Ontology Based Approach for Modeling E-Learning in Healthcare Human Resource Management.
Econ. Comput. Econ. Cybern. Stud. Res. 2015, 49, 18–34.
38. Ruiz-Iniesta, A.; Jiménez-Díaz, G.; Gómez-Albarrán, M. A Semantically Enriched Context-Aware OER Recommendation Strategy
and Its Application to a Computer Science OER Repository. IEEE Trans. Educ. 2014, 57, 255–260. [CrossRef]
39. Raud, Z.; Vodovozov, V. Ontology-Based Design of the Learner’s Knowledge Domain in Electrical Engineering. Electr. Control
Commun. Eng. 2019, 15, 47–53. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.