Graph-Enhanced Knowledge Tracing for Explainable Learner Modeling: A Systematic Literature Review
Abstract
Knowledge Tracing (KT) has become a central approach for modeling students' evolving knowledge states, but conventional sequence-based KT models offer limited representation of relationships among skills, concepts, and assessment indicators, reducing their interpretability for monitoring mastery and learning progression. This study systematically reviews how graph-based and knowledge graph-enhanced KT models have been developed, integrated, and evaluated to support skill mastery, learning outcome monitoring, and assessment-related interpretation. A PRISMA-based Systematic Literature Review was conducted using Scopus and IEEE Xplore, covering publications indexed from 2015 to 2025. From 116 initial records, 20 studies satisfied the eligibility criteria for active graph-enhanced KT and were included in the synthesis corpus, comprising 8 core (40.0%) and 12 supporting (60.0%) studies. Six major integration families were identified, including GCN/GNN-based, Knowledge Graph/ontology-enhanced, heterogeneous or multiplex graph, attention-over-graph, Q-matrix/concept map-based KT, and graph-supported recommendation. Graph-enhanced KT can enrich learner-state representation, support skill and mastery interpretation, and strengthen explainable learner modeling, particularly among core studies. However, active graph-KT integration remains limited, and issues of construct validity, cross-domain generalization, fairness, and deployment-oriented evaluation remain underexplored.
Related
- Surrogate Modeling and Explainable Artificial Intelligence for Complex Systems: A Workflow for Automated Simulation Exploration
- The role of big data analytics in financial fraud detection: A systematic literature review
- A domain knowledge-enhanced lightweight transformer for automatic identification of land-use conflicts in territorial spatial planning texts
- Governing Agentic AI in Africa: A Systematic Literature Review of Ethical Challenges, Framework Gaps, and Ubuntu-Informed Governance Solutions
- Hierarchical Cognitive Structuring and Game Mechanics Alignment in Educational Game Systems: A Systematic Literature Review
BibTeX
@article{nurfaizah2026graphenhanced,
title = {{Graph-Enhanced Knowledge Tracing for Explainable Learner Modeling: A Systematic Literature Review}},
author = {Nurfaizah and R Rizal Isnanto and Imam Tahyudin},
journal = {Journal of Information Systems and Informatics},
year = {2026},
month = oct,
doi = {10.63158/journalisi.v8i5.1844},
url = {https://doi.org/10.63158/journalisi.v8i5.1844},
note = {CC BY},
}
RIS
TY - JOUR
TI - Graph-Enhanced Knowledge Tracing for Explainable Learner Modeling: A Systematic Literature Review
AU - Nurfaizah
AU - R Rizal Isnanto
AU - Imam Tahyudin
PY - 2026
DA - 2026/10/24
JO - Journal of Information Systems and Informatics
DO - 10.63158/journalisi.v8i5.1844
UR - https://doi.org/10.63158/journalisi.v8i5.1844
AB - Knowledge Tracing (KT) has become a central approach for modeling students' evolving knowledge states, but conventional sequence-based KT models offer limited representation of relationships among skills, concepts, and assessment indicators, reducing their interpretability for monitoring mastery and learning progression. This study systematically reviews how graph-based and knowledge graph-enhanced KT models have been developed, integrated, and evaluated to support skill mastery, learning outcome monitoring, and assessment-related interpretation. A PRISMA-based Systematic Literature Review was conducted using Scopus and IEEE Xplore, covering publications indexed from 2015 to 2025. From 116 initial records, 20 studies satisfied the eligibility criteria for active graph-enhanced KT and were included in the synthesis corpus, comprising 8 core (40.0%) and 12 supporting (60.0%) studies. Six major integration families were identified, including GCN/GNN-based, Knowledge Graph/ontology-enhanced, heterogeneous or multiplex graph, attention-over-graph, Q-matrix/concept map-based KT, and graph-supported recommendation. Graph-enhanced KT can enrich learner-state representation, support skill and mastery interpretation, and strengthen explainable learner modeling, particularly among core studies. However, active graph-KT integration remains limited, and issues of construct validity, cross-domain generalization, fairness, and deployment-oriented evaluation remain underexplored.
SN - 2656-5935
SN - 2656-4882
ER -