Knowledge graphs for domain-specific teaching and learning - a systematic review of the construction models and evaluation methods

Akinyinka Tosin Akindele () and Sunday O. Ojo ()

Edelweiss Applied Science and Technology, 2025, vol. 9, issue 8, 1464-1497

Abstract: Knowledge Graphs are structured representations of knowledge that capture concepts and their relationships, facilitating informed decision-making, enhancing efficiency, and enriching learning experiences across various educational contexts. Although interest in Knowledge Graphs (KGs) for teaching and learning (T&L) is increasing, systematic reviews of the latest models, baseline comparisons, and evaluation methods remain limited. This systematic literature review (SLR) aims to address this gap by analyzing the underlying models, baseline algorithms, and evaluation techniques used in the field. Following PRISMA guidelines, a comprehensive search was conducted across five major databases—Scopus, Web of Science, ScienceDirect, ACM Digital Library, and IEEE Xplore—resulting in the identification of 34 relevant articles published between 2018 and 2024. These articles focus on domain-specific KGs applied explicitly to T&L activities. The applications of KGs are categorized into three main areas: Recommendation and Personalized Learning, Concept Mapping and Knowledge Organization, and Information Retrieval and Question Answering. The synthesis of results indicates that deep learning models—particularly BERT and its variants, BiLSTM, and Conditional Random Fields (CRF)—are predominant in knowledge extraction processes. Additionally, Knowledge Graph Embedding (KGE) techniques and Graph Neural Networks (GNNs), such as Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs), are extensively utilized. The review also highlights several limitations, including data scarcity, issues with generalizability, and a lack of standardization. To advance the development of educational KGs, future research should focus on automated data extraction from heterogeneous sources, standardized approaches for entity extraction, consistent evaluation and benchmarking methods, improved interoperability and scalability, as well as enhanced explainability and privacy-preserving techniques.

Keywords: Deep learning; Education; Graph neural network; Knowledge graph; Ontology. (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://learning-gate.com/index.php/2576-8484/article/view/9644/3153 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ajp:edwast:v:9:y:2025:i:8:p:1464-1497:id:9644

Access Statistics for this article

More articles in Edelweiss Applied Science and Technology from Learning Gate
Bibliographic data for series maintained by Melissa Fernandes ().