Graph-Enhanced Knowledge Tracing for Explainable Learner Modeling: A Systematic Literature Review
DOI:
https://doi.org/10.63158/journalisi.v8i5.1844Keywords:
Knowledge Tracing, Knowledge Graph, Graph Neural Networks, Q-matrix, Learning Analytics, Explainable AI in EducationAbstract
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.
Downloads
References
[1] O. O. Komolafe, J. Mustofa, M. J. Daley, D. Walton, and A. Tawiah, “Current applications and outcomes of AI-driven adaptive learning systems in physical rehabilitation science education: A scoping review protocol,” PLoS One, vol. 20, no. 6 JUNE, pp. 1–8, 2025, doi: 10.1371/journal.pone.0325649.
[2] E. Gkintoni, H. Antonopoulou, A. Sortwell, and C. Halkiopoulos, “Challenging Cognitive Load Theory: The Role of Educational Neuroscience and Artificial Intelligence in Redefining Learning Efficacy,” Brain Sci., vol. 15, no. 2, 2025, doi: 10.3390/brainsci15020203.
[3] A. P. Dhakal and B. Devkota, “Use of Artificial Intelligence in Teaching and Learning Environment: A case of using Chat GPT,” NPRC J. Multidiscip. Res., vol. 1, no. 9, pp. 12–23, 2024, doi: 10.3126/nprcjmr.v1i9.74139.
[4] H. Gao, Y. Zeng, B. Ma, and Y. Pan, “Improving Knowledge Learning Through Modelling Students’ Practice-Based Cognitive Processes,” Cognit. Comput., vol. 16, no. 1, pp. 348–365, 2024, doi: 10.1007/s12559-023-10201-z.
[5] L. Lyu, Z. Wang, H. Yun, Z. Yang, and Y. Li, “Deep Knowledge Tracing Based on Spatial and Temporal Representation Learning for Learning Performance Prediction,” Appl. Sci., vol. 12, no. 14, 2022, doi: 10.3390/app12147188.
[6] Z. Wang, W. Wu, C. Zeng, H. Luo, and J. Sun, “Psychological factors enhanced heterogeneous learning interactive graph knowledge tracing for understanding the learning process,” Front. Psychol., vol. 15, 2024, doi: 10.3389/fpsyg.2024.1359199.
[7] J. Wang, Q. Tang, and Z. Zheng, “A knowledge tracing approach with dual graph convolutional networks and positive/negative feature enhancement network,” PLoS One, vol. 20, no. 4 April, pp. 1–15, 2025, doi: 10.1371/journal.pone.0317992.
[8] H. Nakagawa, Y. Iwasawa, and Y. Matsuo, “Graph-based knowledge tracing: Modeling student proficiency using graph neural networks,” Web Intell., vol. 19, no. 1–2, pp. 87–102, 2021, doi: 10.3233/WEB-210458.
[9] P. Pavlik, L. Eglington, and L. Harrell-Williams, “Logistic Knowledge Tracing: A Constrained Framework for Learner Modeling,” IEEE Trans. Learn. Technol., vol. 14, no. 5, pp. 624–639, 2021, doi: 10.1109/TLT.2021.3128569.
[10] J.-J. Vie and H. Kashima, “Knowledge tracing machines: Factorization machines for knowledge tracing,” RIKEN Center for Advanced Intelligence Project, Tokyo, Japan: AAAI Press, 2019, pp. 750–757. doi: 10.1609/aaai.v33i01.3301750.
[11] Y. Shen and Y. Chen, “Knowledge Tracing Enhanced by Graph Convolutional Networks With Self-Supervised Learning,” Int. J. Inf. Commun. Technol. Educ., vol. 21, no. 1, 2025, doi: 10.4018/IJICTE.385130.
[12] N. T. Mai, W. Cao, and W. Liu, “Interpretable Knowledge Tracing via Transformer-Bayesian Hybrid Networks: Learning Temporal Dependencies and Causal Structures in Educational Data,” Appl. Sci., vol. 15, no. 17, pp. 1–26, 2025, doi: 10.3390/app15179605.
[13] Y. Liang, T. Peng, Y. Pu, and W. Wu, “HELP-DKT: an interpretable cognitive model of how students learn programming based on deep knowledge tracing,” Sci. Rep., vol. 12, no. 1, pp. 1–11, 2022, doi: 10.1038/s41598-022-07956-0.
[14] H. Choi, H. Lee, and M.-J. Lee, “Optimal Knowledge Component Extracting Model for Knowledge-Concept Graph Completion in Education,” Ieee Access, vol. 11, pp. 15002–15013, 2023, doi: 10.1109/access.2023.3244614.
[15] M. J. Gomez, Á. Armada Sánchez, M. Albaladejo-González, F. J. García Clemente, and J. A. Ruipérez-Valiente, “Utilising Explainable AI to Enhance Real-Time Student Performance Prediction in Educational Serious Games,” Expert Syst., vol. 42, no. 3, 2025, doi: 10.1111/exsy.70008.
[16] M. Afzaal et al., “Explainable AI for Data-Driven Feedback and Intelligent Action Recommendations to Support Students Self-Regulation,” Front. Artif. Intell., vol. 4, no. November, pp. 1–20, 2021, doi: 10.3389/frai.2021.723447.
[17] Z. Guo, H. Guan, C. He, Y. Xu, and R. Liu, “Knowledge Graph-Enhanced Interleaved Multi-Head Attention Knowledge Tracing,” Int. J. Data Warehous. Min., vol. 21, no. 1, pp. 1–20, 2025, doi: 10.4018/ijdwm.377619.
[18] B. Garzón, V. Perri, L. Qarkaxhija, I. Scholtes, and M. J. Tomasik, “Exploring the structure of the school curriculum with graph neural networks,” J. Comput. Soc. Sci., vol. 8, no. 4, 2025, doi: 10.1007/s42001-025-00420-9.
[19] L. Li and Z. Wang, “Knowledge relation rank enhanced heterogeneous learning interaction modeling for neural graph forgetting knowledge tracing,” PLoS One, vol. 18, no. 12 December, 2023, doi: 10.1371/journal.pone.0295808.
[20] C. Zong, Y. Liu, Y. Hao, and L. Wu, “DPDG-GKT: A Dual-Path Dynamic Gated GNNs Model for Knowledge Tracing,” IEEE Access, vol. 13, pp. 198826–198835, 2025, doi: 10.1109/ACCESS.2025.3635900.
[21] L. Hengyu, T. Zhang, F. Li, Y. Gu, and G. Yu, “Tracking Knowledge Structures and Proficiencies of Students with Learning Transfer,” IEEE Access, vol. 9, pp. 55413–55421, 2021, doi: 10.1109/ACCESS.2020.3032141.
[22] T. Huang, H. Yang, Z. Li, H. Xie, J. Geng, and H. Zhang, “A Dynamic Knowledge Diagnosis Approach Integrating Cognitive Features,” IEEE Access, vol. 9, pp. 116814–116829, 2021, doi: 10.1109/ACCESS.2021.3105830.
[23] L. Huang and K. E. Willcox, “Network models and sensor layers to design adaptive learning using educational mapping,” Des. Sci., vol. 7, 2021, doi: 10.1017/dsj.2021.8.
[24] P. Hu, Z. Li, P. Zhang, J. Gao, and L. Zhang, “DBGCN: A Knowledge Tracing Model Based on Dynamic Breadth Graph Convolutional Networks,” Int. J. Web-Based Learn. Teach. Technol., vol. 19, no. 1, 2024, doi: 10.4018/IJWLTT.342848.
[25] L. Qiu and S. Sun, “Integrating Multiplex Heterogeneous Network for Knowledge Tracing,” Int. Arab J. Inf. Technol., vol. 22, no. 2, pp. 236–247, 2025, doi: 10.34028/iajit/22/2/3.
[26] Y. Wang, Y. Huo, C. Yang, X. Huang, D. Xia, and F. Feng, “Knowledge ontology enhanced model for explainable knowledge tracing,” J. King Saud Univ. - Comput. Inf. Sci., vol. 36, no. 5, 2024, doi: 10.1016/j.jksuci.2024.102065.
[27] J. Pan, Z. Dong, L. Yan, and X. Cai, “Knowledge Graph and Personalized Answer Sequences for Programming Knowledge Tracing,” Appl. Sci., vol. 14, no. 17, 2024, doi: 10.3390/app14177952.
[28] Z. Yan, H. Du, Z. Lin, and Z. Jianhua, “Personalization Exercise Recommendation Framework based on Knowledge Concept Graph,” Comput. Sci. Inf. Syst., vol. 20, no. 2, pp. 857–878, 2023, doi: 10.2298/CSIS220706024Y.
[29] J. Xia, A. Li, H. Yin, and G. Jin, “Enhancing knowledge tracing through course map and question difficulty analysis,” Array, vol. 28, no. October, p. 100523, 2025, doi: 10.1016/j.array.2025.100523.
[30] G. Yu, Z. Xie, G. Zhou, Z. Zhao, and J. X. Huang, “Exploring long- and short-term knowledge state graph representations with adaptive fusion for knowledge tracing,” Inf. Process. Manag., vol. 62, no. 3, 2025, doi: 10.1016/j.ipm.2025.104074.
[31] X. Liu, P. Hu, and Y. P. Su, “Integrating individualised and similar group in knowledge tracing,” Comput. Electr. Eng., vol. 123, 2025, doi: 10.1016/j.compeleceng.2025.110105.
[32] P. Zhang, P. Hu, G. Li, Y. Lv, and M. Wan, “DHKFN: Knowledge Tracking Model Based on Deep Hierarchical Knowledge Fusion Networks,” Int. J. Knowl. Manag., vol. 20, no. 1, 2024, doi: 10.4018/IJKM.358011.
[33] O. M. Teodorescu, P. S. Popescu, L. M. Mocanu, and M. C. Mihaescu, “Continuous Student Knowledge Tracing Using SVD and Concept Maps,” Adv. Electr. Comput. Eng., vol. 21, no. 1, pp. 75–82, 2021, doi: 10.4316/AECE.2021.01008.
[34] S. Orlando, E. Gaudioso, and F. de la Paz, “Toward Embedding Robotics in Learning Environments With Support to Teachers: The IDEE Experience,” IEEE Trans. Learn. Technol., vol. 17, pp. 874–884, 2024, doi: 10.1109/TLT.2023.3339882.
[35] A. Nyamen Tato and R. Nkambou, “Infusing Expert Knowledge Into a Deep Neural Network Using Attention Mechanism for Personalized Learning Environments,” Front. Artif. Intell., vol. 5, 2022, doi: 10.3389/frai.2022.921476.
[36] N. Yanes, A. M. Mostafa, M. Ezz, and S. N. Almuayqil, “A Machine Learning-Based Recommender System for Improving Students Learning Experiences,” IEEE Access, vol. 8, pp. 201218–201235, 2020, doi: 10.1109/ACCESS.2020.3036336.
[37] Y. Chen, S. Wang, F. Jiang, Y. Tu, and Q. Huang, “DCKT: A Novel Dual-Centric Learning Model for Knowledge Tracing,” Sustain., vol. 14, no. 23, pp. 1–20, 2022, doi: 10.3390/su142316307.
[38] S. Wan, Z. Fu, and C. Wei, “An exercise recommendation approach via multi-behavior interactive perception and semantic-enhanced knowledge graph,” J. King Saud Univ. - Comput. Inf. Sci., vol. 37, no. 9, 2025, doi: 10.1007/s44443-025-00322-w.
[39] K. Takami, Y. Dai, B. Flanagan, and H. Ogata, “Educational Explainable Recommender Usage and its Effectiveness in High School Summer Vacation Assignment,” in ACM International Conference Proceeding Series, Academic Center for Computing and Media Studies, Kyoto, Kyoto, Japan: Association for Computing Machinery, 2022, pp. 458–464. doi: 10.1145/3506860.3506882.
[40] L. Zhang, X. Zeng, and P. Lv, “Higher Education-Oriented Recommendation Algorithm for Personalized Learning Resource,” Int. J. Emerg. Technol. Learn., vol. 17, no. 16, pp. 4–20, 2022, doi: 10.3991/ijet.v17i16.33179.
[41] W. Hussain, W. G. Spady, M. T. Naqash, S. Z. Khan, B. A. Khawaja, and L. Conner, “ABET Accreditation during and after COVID19 - Navigating the Digital Age,” IEEE Access, vol. 8, pp. 218997–219046, 2020, doi: 10.1109/ACCESS.2020.3041736.
[42] B. Zhang, A. Meroño-Peñuela, and E. Simperl, “Towards Explainable Automated Knowledge Engineering with Human-in-the-loop,” vol. 16, no. 5, pp. 1–36, 2025, doi: 10.1177/22104968251382171.
[43] Y. Liu, W. Ji, and G. Zhou, “Spatiotemporal fusion knowledge tracking model based on spatiotemporal graph and fourier graph neural network,” J. King Saud Univ. - Comput. Inf. Sci., vol. 37, no. 6, 2025, doi: 10.1007/s44443-025-00138-8.
[44] S. Tahir, Y. Hafeez, M. Humayun, F. Ahmad, M. Khan, and M. Shaheen, “Harnessing hybrid deep learning approach for personalized retrieval in e-learning,” PLoS One, vol. 19, no. 11 November, 2024, doi: 10.1371/journal.pone.0308607.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information Systems and Informatics
This work is licensed under a Creative Commons Attribution 4.0 International License.
Author's Declaration
- The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
- The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
- The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
- The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
- The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
- The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
- If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
- The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights
