📄 Sciences Methods and Technologies
International Journal (SciMeTech)

Volume 2 · Issue 1 · 2026
ISSN: 3085-5284
A Hybrid Recommendation System for Adaptive Learning: Combining Graph, DKT, and ZPD
Yassine Ennhili, Yassine Afoudi
Pages 47–54 · Cadi Ayyad University (UCA), Faculty of Sciences Semlalia, Laboratory of Computer Science and Smart Systems (LISI), Marrakesh, Morocco
⬇ PDF
Abstract
The rapid expansion of online education has created a pressing need for adaptive systems capable of guiding students through complex curricula. However, most existing platforms rely on static, linear learning paths that fail to account for the heterogeneous backgrounds, prior knowledge, and evolving cognitive states of individual learners. This often results in disengagement, suboptimal retention, and elevated dropout rates. To address these challenges, we propose a novel Hybrid Recommendation System designed to optimize personalized learning trajectories in a pedagogically sound manner. Our architecture integrates three core components: (1) a Prerequisite Graph to enforce logical pedagogical structure and dependencies among concepts, ensuring foundational knowledge is built sequentially; (2) Deep Knowledge Tracing (DKT) utilizing Long Short-Term Memory (LSTM) networks to model the temporal evolution of a learner's knowledge state based on interaction histories; and (3) a Zone of Proximal Development (ZPD) selector, inspired by Vygotsky's theory, which prioritizes tasks that are challenging yet achievable to foster optimal cognitive growth and maintain learner motivation. The ZPD module shifts the focus from merely maximizing immediate success to accelerating long-term learning velocity by selecting content at an appropriate difficulty level. We validated our system on a dataset of students engaging with programming courses in Python, JavaScript, and SQL. The implemented hybrid approach (Graph + DKT + ZPD) demonstrates the viability of combining structural, temporal, and pedagogical signals for next-generation intelligent tutoring systems that promote deeper engagement and knowledge retention.
Keywords: Recommended Systems, Adaptive Learning, Deep Knowledge Tracing, Collaborative Filtering, Educational Data Mining

References

  1. Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L. J., & Sohl-Dickstein, J. (2015). Deep knowledge tracing. Advances in Neural Information Processing Systems, 28.
  2. Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, 42(8), 30-37.
  3. Vygotsky, L. S. (1978). Mind in society: The development of higher psychological processes. Harvard University Press.
  4. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT.
  5. Pandey, S., & Karypis, G. (2019). A self-attentive model for knowledge tracing. In Proceedings of the 12th International Conference on Educational Data Mining (pp. 384-389).
  6. Zhang, J., Shi, X., King, I., & Yeung, D.-Y. (2017). Dynamic key-value memory networks for knowledge tracing. In Proceedings of the 26th International Conference on World Wide Web (pp. 765-774).
  7. Khalil, H., & Ebner, M. (2014). MOOCs: A systematic study of the published literature 2012-2014. Proceedings of EdMedia, 605-614.
  8. Jordan, K. (2015). Massive open online course completion rates revisited: Assessment, length and attrition. The International Review of Research in Open and Distributed Learning, 16(3).
  9. Drachsler, H., Verbert, K., Santos, O. C., & Manouselis, N. (2015). Panorama of recommender systems to support learning. In F. Ricci et al. (Eds.), Recommender systems handbook (pp. 421-451). Springer.
  10. Thai-Nghe, N., Drumond, L., Krohn-Grimberghe, A., & Schmidt-Thieme, L. (2010). Recommender systems for e-learning: Toward a unified approach. International Journal of Distance Education Technologies (IJDET), 8(3), 1-20.
  11. Bobadilla, J., Ortega, F., Hernando, A., & Gutiérrez, A. (2013). Recommender systems survey. Knowledge-Based Systems, 46, 109-132.
  12. Wei, Y., He, L., & Nian, K. (2011). Investigation of cold-start problem in educational recommender systems. International Journal of Information and Education Technology, 1(2), 166.
  13. Nakagawa, H., Iwasawa, Y., & Matsuo, Y. (2019). Graph-based knowledge tracing: Modeling student proficiency using graph neural network. In IEEE/WIC/ACM International Conference on Web Intelligence (pp. 156-163).
  14. Huang, Z., Liu, Q., Chen, E., Wu, H., Su, Y., & Chen, G. (2019). Exploring the impact of knowledge tracing models on learning recommendation. IEEE Transactions on Knowledge and Data Engineering.
  15. Tarus, J. K., Niu, Z., & Kalai, D. (2018). A hybrid knowledge-based recommender system for e-learning based on ontology and sequential pattern mining. Future Generation Computer Systems, 72, 37-48.
  16. Aldowah, H., Al-Samarraie, H., & Alzahrani, A. I. (2019). Factors affecting student dropout in MOOCs: A review. Journal of Computing in Higher Education, 31, 1-21.
  17. Hew, K. F. (2016). Student participation in massive open online courses: An analysis of interaction activities and attitudinal learning. International Journal of Educational Technology in Higher Education, 13(1), 1-19.
  18. Lian, D. (2012). A survey on recommender systems for e-learning. Intelligent Networking and Collaborative Systems.
  19. Pazzani, M. J., & Billsus, D. (2007). Content-based recommendation systems. In P. Brusilovsky et al. (Eds.), The adaptive web (pp. 325-341). Springer.
  20. Shu, J., Shen, X., Liu, H., & Liu, B. (2018). Integrating computing with learning: A review of research on recommender systems for e-learning. IEEE Access, 6, 52702-52714.
  21. Yang, Y., Shen, J., Qu, Y., Liu, Y., Wang, K., Zhu, Y., Zhang, W., & Yu, Y. (2020). GIKT: A graph-based interaction model for knowledge tracing. ECML-PKDD.
  22. Liu, H., Wang, Y., & Wang, X. (2019). A hybrid recommendation algorithm based on attention mechanism and knowledge graph. Procedia Computer Science.
  23. Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2020). A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 32(1), 4-24.
  24. Luckin, R. (2008). The learner centric ecology of resources: A framework for using technology to scaffold learning. Computers & Education, 50(2), 449-462.
  25. Yeung, C., & Yeung, D. (2018). Addressing two problems in deep knowledge tracing via prediction-consistent regularization. arXiv preprint arXiv:1806.02180.
  26. Maruyama, M. H. M., Silveira, L. W., de Oliveira, J. P. M., Gasparini, I., & Maran, V. (2023). Hybrid recommender system for educational resources to the smart university campus domain. In Proceedings of the 15th International Conference on Computer Supported Education (CSEDU 2023) (Vol. 1, pp. 47-56). SCITEPRESS.
  27. Bhattacharjee, I., & Wayllace, C. (2025). Cold start problem: An experimental study of knowledge tracing models with new students. arXiv preprint arXiv:2505.21517.
  28. Zhou, X., Zhang, Z., Xie, X., & Zhang, J. (2025). Deep learning based knowledge tracing in intelligent tutoring systems. Scientific Reports, 15(21395), 1-15.
  29. Burke, R. (2002). Hybrid recommender systems: Survey and experiments. User Modeling and User-Adapted Interaction, 12(4), 331-370.
  30. Gomez-Uribe, C. A., & Hunt, N. (2015). The Netflix recommender system: Algorithms, business value, and innovation. ACM Transactions on Management Information Systems, 6(4), 1-19.
  31. Feng, M., Heffernan, N., & Koedinger, K. R. (2009). Addressing the assessment challenge with an online system that tutors as it assesses. User Modeling and User-Adapted Interaction, 19(3), 243-266.
SciMeTech · Volume 2, Issue 1 · 2026 · ISSN 3085-5284