X International conference�“Information Technology and Implementation” (IT&I-2023)�Kyiv, Ukraine
1
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System
Kostiantyn Tkachenko, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Kyiv, Ukraine
Olha Tkachenko, State University of Infrastructure and Technologies, Kyiv, Ukraine
Oleksandr Tkachenko, State University of Infrastructure and Technologies, Kyiv, Ukraine
�
Dedicated to the tenth anniversary of the Faculty of Information Technology
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System�INTRODUCTION
Use of traditional tools and methods of knowledge management in learning associated with undifferentiated events is not targeted and the only source of knowledge transfer when learning in the modern information environment. Interaction with students should be enriched by the use of differentiated tools and methods for transmitting, applying and creating knowledge.
One of the approaches to increasing the effectiveness of learning is the individualization of learning, and in our time, most often e-learning. The interaction in e-learning and/or knowledge management in learning management systems (LMS) occurs not between person and management system, but between the digital footprint, digital learning artifacts and the intelligent knowledge management system.
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System �INTRODUCTION
This feature gives rise to a number of new problems such as:
• finding ways to present personalized learning data;
• modeling of digital artifacts created by e-learning systems;
• intellectualization of the analysis of learning data and/or knowledge;
• automation of adaptation and updating of educational content;
• individualization of learning processes.
The article describes an approach to solving problems using knowledge graphs, ontologies and so-called “machine” learning technologies.
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System �BUILDING KNOWLEDGE BASE IN E-LEARNING SYSTEM �
To describe subject areas (SA), RDF is used, the main element of which is: <subject, predicate, object>, where subjects and objects are unique entities to represent more complex structures.
Each entity is a resource identifier – URI.
Let V, B, A be disjoint infinite sets of URIs (V ∩ B ∩ L = ∅), unnamed vertices and literals, respectively.
RDF graph G = (T, P, M, A), where T ⊂ ( V ∪ B ∪ A) is finite set of RDF terms corresponding to the nodes of the graph; R ⊆ T x T – finite set of arcs connecting RDF terms; M ⊂ V – set of unique labels defined using URI;
A: R → 2M – mapping arcs to set of labels.
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System �BUILDING KNOWLEDGE BASE IN E-LEARNING SYSTEM �
Examples of ontologies used to create specialized e-learning systems, for example:
• AIISO – describing the internal organizational structure of the educational process
• BIBO – describing recommended literature, scientific publications, textbooks, monographs
• MA-ONT – describing media resources (lectures are associated with video materials)
• TEACH – describing educational content (dictionary with which teachers can link objects of online courses)
• FOAF – defines expressions used in statements about an object (for example, about the object “student” – this is the name, gender, age, etc.)
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System �BUILDING KNOWLEDGE BASE IN E-LEARNING SYSTEM �
To individualize learning, it is necessary to use a student model, without which it is impossible to create an adequate individualization system.
The online course consists of many modules and topics within modules.
Semantic dependencies between modules are indicated in the course prerequisites (descriptions of courses that must be studied before studying the educational content of this online course).
For each specific student, you can build a chain of modules or courses that need to be studied.
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System �BUILDING KNOWLEDGE BASE IN E-LEARNING SYSTEM �
Let's look at an example. The student has chosen an introductory course in discrete mathematics and in order to understand what a Turing machine is, he must study the concepts associated with an algorithm and its formal description, which are introduced in the Theory of Algorithms course.
But including the entire course Theory of Algorithms or a module on formalizing algorithms into an individual learning path will be redundant for the student. It is enough to simply limit yourself to the necessary components of educational content, otherwise the student may end up with an overloaded trajectory.
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System� �BUILDING AND USING INDIVIDUAL LEARNING TRAJECTORIES IN E-LEARNING SYSTEM
It is difficult to provide for all points of an individual learning trajectory, due to the following reasons:
1. An individual learning trajectory is the result of the projection of several ontological models onto each other (course model, knowledge assessment model, student cognitive model, etc.).
2. During the learning process, some models change (the student’s cognitive model is replenished with new entities; teachers can change course models and update educational content; models of individual learning trajectories change as new data accumulate).
3. The learning process is influenced by external factors (market requirements, economic, social, etc.)
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System� �BUILDING AND USING INDIVIDUAL LEARNING TRAJECTORIES IN E-LEARNING SYSTEM
Personalizing e-learning is technology for creating intellectualization and management systems in education, which should include, in particular:
– methods of ontological engineering
– machine learning methods
– semantic analysis and search tools
– tools for developing recommendations
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System��BUILDING AND USING INDIVIDUAL LEARNING TRAJECTORIES IN E-LEARNING SYSTEM
The architecture of e-learning systems that support individualized learning should include:
• Integration level (data providers to the LMS database; API for external data sources).
• Data management layer (metadata storage; machine learning models for creating or extending ontologies; templates for constructing semantic queries).
• Level of data analysis and intellectual services (course ontologies that take into the account individualization; cognitive ontological models of the student; rules for creating an individual learning trajectory).
• Application and interface level (recommendation subsystems for interaction with students; interactive visualization of technical equipment).
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System��MODELING IN E-LEARNING SYSTEM BASED ON KNOWLEDGE GRAPH
The student’s acquired knowledge graph is formed from a variety of SA description concepts and is a subset of the general knowledge graph of all online courses.
At the beginning of leaning (study), this knowledge graph is empty.
Then a starting set of concepts is placed in it, which is determined by the result of the student’s starting test or obtained from studying the introductory course.
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System��MODELING IN E-LEARNING SYSTEM BASED ON KNOWLEDGE GRAPH
The knowledge graph of particular student contains so-called “knowledge gaps”, which are identified when compared with the general knowledge graph (topic, course, discipline, etc.).
To do this, the student’s knowledge graph is projected onto the discipline’s knowledge graph, which helps to restore the missing nodes and add connections to the discipline’s knowledge graph to determine the part of the individual learning trajectory that has already been completed.
After identifying missing concepts in students' knowledge graphs, it is necessary to determine the relationships between them in order to formulate sequence for their study.
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System��MODELING IN E-LEARNING SYSTEM BASED ON KNOWLEDGE GRAPH
Significant amount of information about learning effectiveness can be obtained by analyzing a student's digital footprint by examining digital artifacts, which may have the following types of data:
• logs of user behavior in the system (number of visits to individual pages, time spent on each page, actions on pages, etc.)
• user actions with educational content
• activity when interacting with other users and the lecturer through social services (number of questions and answers, frequency of sending messages, etc.)
• text data generated by the student when using general chat or email;
• data includes knowledge tests (closed and open tests, results of practical tasks, etc.)
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System��E-LEARNING SYSTEM: ONTOLOGICAL MODELING�
The formation and modification of an individualized learning path in an e-learning system, when courses are not studied as a whole, but as separate components of educational content, can lead to a situation of chaotic mixing of the topics being studied.
To eliminate this situation in the e-learning system, it is necessary to control the semantic similarity of the studied set of topics and the content of the discipline.
This is based on the use of approximation of the studied concepts by course ontologies, which makes it possible to form an individualized learning path with a focus on the subject of study by ranking the topics (modules, components, concepts) of the educational content of the course.
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System��E-LEARNING SYSTEM: ONTOLOGICAL MODELING�
Assessing the semantic similarity of the planned and actual learning trajectory takes into the account three aspects that link the compared objects of the knowledge graph: hierarchy, proximity and specificity.
Semantic similarity assessment. uses hierarchical similarity methods and metrics to measure hierarchical similarity between two entities when the nodes of the entities being compared in the graph have a common ancestor that is furthest from the root of the hierarchy tree and lies on both trajectories from those vertices to the root.
Semantic similarity assessment uses knowledge mapped in relationships and knowledge graph class hierarchies to compare two pairs.
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System��E-LEARNING SYSTEM: ONTOLOGICAL MODELING�
During the learning process, student’s knowledge graph is formed, replenished with references to the concepts of already studied SA.
The totality of these connections forms the cognitive profile of the student. For each link in the learning process, certain weight is calculated, characterizing the level of knowledge of particular topic.
The student’s ontology contains the concepts and connections necessary for modeling: what topics and concepts were studied; assessment of the quality of learning (level of learning); characteristics of the student himself, obtained by analyzing his actions while studying certain topic (course, discipline, SA).
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System��E-LEARNING SYSTEM: ONTOLOGICAL MODELING�
Additional tools for managing educational content and presenting it to students show positive dynamics in the results of students studying a specific course in accordance with their individual learning trajectory.
The effectiveness of using an individual learning path is also determined by the fact that the e-learning system provides the student with the opportunity to apply knowledge, such as “best practices”, “lessons learned”, where the analysis is carried out not only of the student’s successful and unsuccessful answers.
An individualized approach involves annotation of typical errors, shortcomings and omissions (students are clearly shown what real errors may look like and are shown ways to find a solution to a specific problem).
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System��E-LEARNING SYSTEM: ONTOLOGICAL MODELING�
The ontological model of the course (discipline, SA) is formed for its joint use by teachers, SA experts, stakeholders, etc.).
The ontological model and knowledge graphs make it possible to separate knowledge about SA (course, discipline) from the knowledge acquired by students.
The ontological model can be used when designing academic discipline programs that take into the account the possibility of using individualized learning paths for specific students, their needs and levels of prior knowledge, planning the structure of educational content, assessing the student’s level of knowledge and competencies, and solving other problems.
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Using Ontologies and Knowledge Graphs to Individualize in E-Learning System��CONCLUSION
An approach is proposed that involves performing, in particular:
• analysis of existing knowledge management tools in the learning process and presentation of educational content to students
• formation of an Individualized learning path and the corresponding graph of the student’s knowledge
• adaptation and modification during the learning process of the Individualized learning path and the corresponding student knowledge graph
The practical application of the proposed approach to e-learning, based on the individualization of learning processes, demonstrates its suitability for solving set educational tasks, increasing student achievement and engagement.
Information Technology and Implementation, November 20, 2023, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
Thanks for your attention to our work!!