Mentora ChatBot as an Intelligent Recommender System in Education

Olga Dukić1[0009−0004−1694−9592] and Marija Blagojević1[0000−0003−4186−0448]
University of Kragujevac, Faculty of Technical Sciences Čačak, Department of Information Technologies, Čačak, Serbia
dukicolga678@gmail.com,
marija.blagojevic@ftn.kg.ac.rs
DOI: 10.46793/eLearning2025.171D

 

Abstract.  The development and evaluation of the Mentora ChatBot, an educational conversational agent designed to provide personalized learner support, are presented. Mentora combines large language models (LLMs) with sequential modeling of user behavior, relying on a BiLSTM architecture alongside heuristic rules to generate recommendations aligned with learners’ needs. The system was developed and initially tested during preparatory classes for the final exam in mathematics and the Serbian language, conducted from February–June 2025 at a private educational institution. Twenty two eighth-grade students participated, and more than 600 interaction logs were analyzed. Substantial gains in recommendation precision and acceptance were observed with the integration of the BiLSTM module, relative to a purely heuristic baseline. An empirically grounded approach is introduced that couples LLM-driven dialogue with personalization of learning trajectories. Directions for further development are outlined, including the adaptation of recommendations to diverse learner profiles and the incorporation of explainable recommendations (explainable AI).

Keywords:  Recommender systems · educational chatbot · BiLSTM · log analysis.

Acknowledgments This study was supported by the Ministry of Science, Technological Development and Innovation of the Republic of Serbia, and these results are parts of the Grant No. 451-03-136/2025-03/200132, with University of Kragujevac- Faculty of Technical Sciences Čačak.

References

  1. Drachsler, H., Kalz, M.: Panorama of recommender systems to support learning. In: Ricci, F., Rokach, L., Shapira, B. (eds.) Recommender Systems Handbook, pp. 421–451. Springer (2015). https://doi.org/10.1007/978-1-4899-7637-6_12
  2. Han, J., Kamber, M.: Data Mining: Concepts and Techniques. Elsevier, 2nd edn. (2006)
  3. Jannach, D., Resnick, P., Tuzhilin, A., Zhang, Y.: Conversational recommender systems. Foundations and Trends in Information Retrieval 16(1), 1–101 (2021). https://doi.org/10.1561/1500000068
  4. Liu, B.: Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data. Springer, 2nd edn. (2011)
  5. Manouselis, N., Drachsler, H., Verbert, K., Duval, E.: Recommender Systems for Learning. SpringerBriefs in Electrical and Computer Engineering, Springer (2012). https://doi.org/10.1007/978-1-4614-4361-2
  6. Okubo, F., Yamashita, T., Shimada, A., Ogata, H.: Learning analytics to improve learning outcomes: A case study of a flipped classroom. Research and Practice in Technology Enhanced Learning 12(1), 1–23 (2017). https://doi.org/10.1186/ s41039-017-0043-6
  7. Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L., Sohl Dickstein, J.: Deep knowledge tracing. In: Advances in Neural Information Pro cessing Systems (NeurIPS) (2015)
  8. Quadrana, M., Cremonesi, P., Jannach, D.: Sequence-aware recommender systems. ACM Computing Surveys 51(4), 66:1–66:36 (2018). https://doi.org/10.1145/ 3190616
  9. Ricci, F., Rokach, L., Shapira, B.: Introduction to recommender systems handbook. In: Recommender Systems Handbook, pp. 1–35. Springer (2011). https://doi. org/10.1007/978-0-387-85820-3_1
  10. Roux, L., Dagorret, P., Etcheverry, P., Nodenot, T., Marquesuzaa, C., Lopisteguy, P.: A multi-layer architecture for an e-learning hybrid recommender system. In: Proceedings of the 18th International Conference on Cognition and Exploratory Learning in Digital Age (CELDA 2021). pp. 179–187 (2021)
  11. Russell, M.A.: Mining the Social Web. O’Reilly Media, 1st edn. (2013)
  12. Sun, Y., Papamitsiou, Z., Giannakos, M.: Design and evaluation of a conversational recommender system for learning pathways. IEEE Transactions on Learning Technologies 16(1), 95–108 (2023). https://doi.org/10.1109/TLT.2022.3185156
  13. Zhang, Y., Chen, X.: Explainable recommendation: A survey and new perspectives. Foundations and Trends in Information Retrieval 14(1), 1–101 (2020). https:// doi.org/10.1561/1500000066

 

 

Izvor: Proceedings of the 16th International Conference on e-Learning (ELEARNING2025)