Abstract
Personalized course recommendations represent a significant problem in extensive e-learning platforms, as student preferences are in constant flux and educational environments are increasingly influenced by IoT-enabled interactions. Traditional recommendation algorithms generally regard user behavior as static or minimally contextualized, hence constraining their efficacy in dynamic and diverse learning settings. This research presents a context-sensitive sequential recommendation framework that concurrently models uncertainty, temporal learning patterns, and real-time contextual awareness. The proposed approach utilizes Conditional Variational Autoencoders to develop resilient latent representations of learners and courses amidst sparse and noisy interaction data, while a Transformer-based sequential model captures long-term dependencies in learning trajectories. In contrast to current methodologies, contextual signals obtained from IoT-enabled learning environments are explicitly integrated and amalgamated into the sequential decision-making process, enabling suggestions to adjust to situational learning settings rather than depending exclusively on prior encounters. The model is trained with a cohesive objective that harmonizes representation consistency and ranking accuracy, facilitating stable personalization across various learner profiles. Experimental assessments on various real-world MOOC datasets reveal consistent and statistically significant improvements over competitive baselines in both ranking and error metrics, validating the efficacy of incorporating uncertainty-aware modeling with context-driven sequential learning. The suggested method reinterprets course recommendation as a dynamic, context-sensitive process and establishes a scalable framework for intelligent e-learning systems designed to facilitate personalized learning trajectories within IoT-integrated digital education environments.
Similar content being viewed by others
Data availability
The datasets utilized and/or examined in the present investigation are accessible from the corresponding author upon reasonable request.
References
Garrison, D. R. & Anderson, T. E-Learning in the 21st Century: A Community of Inquiry Framework for Research and Practice (Routledge, 2021).
Bozkurt, A. & Zawacki-Richter, O. Trends and Patterns in Distance Education (2014–2019): A Synthesis of Scholarly Publications and a Visualization of the Intellectual Landscape. Int. Rev. Res. Open. Distrib. Learn. 22 (2), 1–341. https://doi.org/10.19173/irrodl.v22i2.5381 (2021).
Haron, H. et al. The Platform of MOOC (Massive Open Online Course) on Open Learning: Issues and Challenges. Int. J. Mod. Educ. 1(3) 1–9https://doi.org/10.35631/ijmoe.13001 (2019).
Hazrati, N. & Ricci, F. Choice models and recommender systems effects on users’ choices, User Model. User-Adap. Inter. 34(1), 109–145 https://doi.org/10.1007/s11257-023-09366-x (2024).
Zhang, S., Yao, L., Sun, A. & Tay, Y. Deep Learning Based Recommender System: A Survey and New Perspectives. ACM Comput. Surv. 52(1) 1–38 https://doi.org/10.1145/3285029 (2019).
Huang, C. et al. XKT: Toward Explainable Knowledge Tracing Model With Cognitive Learning Theories for Questions of Multiple Knowledge Concepts. IEEE Trans. Knowl. Data Eng. 36 (11), 7308–7325. https://doi.org/10.1109/TKDE.2024.3418098 (2024).
Nyaga, J. M. IoT-Enhanced Adaptive Learning Environments: Personalized Online Education for the Digital Age. Afr. J. Comput. Inf. Syst. 7, 1–14. https://doi.org/10.1234/ajcis.v7iX.2 (Oct. 2023). no. X.
Shireesha, M. & Jala, J. The Role of Artificial Intelligence in Personalized Learning: A Pathway to Inclusive Education. Libr. Prog.-Libr. Sci. Inf. Technol. Comput. 44(3), 21746 (2024).
da Silva, F. L. et al. Mar., A systematic literature review on educational recommender systems for teaching and learning: research trends, limitations and opportunities. Educ. Inf. Technol. 28(3) 3289–3328 https://doi.org/10.1007/s10639-022-11341-9 (2023).
Panteli, A. & Boutsinas, B. Addressing the Cold-Start Problem in Recommender Systems Based on Frequent Patterns. Algorithms 16 (4), 182. https://doi.org/10.3390/a16040182 (2023).
Hodovychenko, M. A. & Gorbatenko, A. A. Recommender systems: models, challenges and opportunities. Herald Adv. Inf. Technol. 6 (4), 308–319. https://doi.org/10.15276/hait.06.2023.20 (2023).
Zhou, Z., Shojafar, M., Alazab, M., Abawajy, J. & Li, F. AFED-EF: An Energy-Efficient VM Allocation Algorithm for IoT Applications in a Cloud Data Center. IEEE Trans. Green. Commun. Netw. 5 (2), 658–669. https://doi.org/10.1109/TGCN.2021.3067309 (2021).
Wei, R. & Mahmood, A. Recent Advances in Variational Autoencoders With Representation Learning for Biomedical Informatics: A Survey. IEEE Access. 9, 4939–4956 https://doi.org/10.1109/ACCESS.2020.3048309 (2020).
Singh, M. Scalability and sparsity issues in recommender datasets: a survey. Knowl. Inf. Syst. 62 (1), 1–43. https://doi.org/10.1007/s10115-018-1254-2 (2020).
Shafik, W. Towards Trustworthy and Explainable AI Educational Systems, in Explainable AI for Education: Recent Trends and Challenges, T. Singh, S. Dutta, S. Vyas, and Á. Rocha, Eds. Cham: Springer, pp. 15–32 https://doi.org/10.1007/978-3-031-72410-7_2 (2024).
Bodduluri, K. C., Palma, F., Kurti, A., Jusufi, I. & Löwenadler, H. Exploring the Landscape of Hybrid Recommendation Systems in E-Commerce: A Systematic Literature Review. IEEE Access. 12, 28273–28296 https://doi.org/10.1109/ACCESS.2024.3363256 (2024).
Xu, F., Yang, H. & Alouini, M. Energy Consumption Minimization for Data Collection From Wirelessly-Powered IoT Sensors: Session-Specific Optimal Design With DRL. IEEE Sens. J., 22(20), 19886–19896. doi: https://doi.org/10.1109/JSEN.2022.3205017 (2022).
Petrov, A. V. & Macdonald, C. Transformers for Sequential Recommendation, in Advances in Information Retrieval, (eds Goharian, N. et al.) Cham: Springer, 369–376 https://doi.org/10.1007/978-3-031-56069-9_49. (2024).
Ma, W., Wu, J., Song, D., Chen, Z. & Huang, T. HVAE-DC: A hierarchical variational autoencoder-based deep clustering model for multi-level driving behavior. Expert Syst. Appl. 305, 130882. https://doi.org/10.1016/j.eswa.2025.130882 (2026).
Sun, F. et al. BERT4Rec: Sequential recommendation with bidirectional encoder representations from transformer. In Proceedings of the 28th ACM international conference on information and knowledge management (pp. 1441–1450). (2019).
Yaghoobi, A. & Harandi, M. N. Quantum-Enhanced Adaptive Scheduling for Real-Time IoT Task Optimization in Fog-Cloud Systems. Computer Networks, 112088. (2026).
Amin, S. et al. An adaptable and personalized framework for top-N course recommendations in online learning, Sci. Rep., 14, 10382 https://doi.org/10.1038/s41598-024-56497-1 (2024).
Li, J., Wang, Y. & McAuley, J. Time interval aware self-attention for sequential recommendation. In Proceedings of the 13th international conference on web search and data mining (pp. 322–330). (2020).
Zhang, Q., Li, Y., Zhang, G. & Lu, J. A recurrent neural network-based recommender system framework and prototype for sequential E-learning, in Developments of Artificial Intelligence Technologies in Computation and Robotics, World Scientific Proceedings Series on Computer Engineering and Information Science, pp. 488–495 https://doi.org/10.1142/9789811223334_0059 (2020).
Sun, W., Liu, Z., Fan, X., Wen, J. R. & Zhao, W. X. Towards Efficient and Effective Transformers for Sequential Recommendation, in Database Systems for Advanced Applications, (eds Wang, X. et al.) Cham: Springer, 347–362, doi: https://doi.org/10.1007/978-3-031-30672-3_23. (2023).
Ali, M. et al. IoTFLiP: IoT-based flipped learning platform for medical education. Digit. Commun. Netw. 3 (3), 188–194. https://doi.org/10.1016/j.dcan.2017.03.002 (2017).
Li, W. et al. Neural nonnegative latent factorization of tensors model with acceleration and unconstraint. IEEE Transactions on Systems, Man, and Cybernetics: Systems. (2025).
Wu, L., Zhou, T., Lai, Y., Lin, H. & Hu, J. Personalized Asynchronous Federated Learning for Intelligent Vehicular Computing (IEEE Transactions on Consumer Electronics, 2025).
Wang, Z., Sun, C. A. & Aiello, M. Context-aware IoT Service Recommendation: A Deep Collaborative Filtering-based Approach, in Proc. IEEE Int. Conf. Web Services (ICWS), Barcelona, Spain, Jul. pp. 171–180, (2022). https://doi.org/10.1109/ICWS55610.2022.00035
Vishnu Shankar, S., Naffees Gowsar, S. R. & Manjubala, M. in Variational Autoencoders (VAEs), in Revolution with Generative AI: Trends and Techniques. 35–50 (eds Gayathri, N., Rakesh, S., kumar & Rocha, A.) (Springer, 2025). https://doi.org/10.1007/978-3-031-91660-1_3
Carraro, T., Polato, M., Bergamin, L. & Aiolli, F. Conditioned Variational Autoencoder for Top-N Item Recommendation, in Artificial Neural Networks and Machine Learning – ICANN 2022, (eds Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A. & Aydin, M.) Cham: Springer, 776–787, https://doi.org/10.1007/978-3-031-15931-2_64. (2022).
Çano, E. & Morisio, M. Hybrid recommender systems: A systematic literature review. Intell. Data Anal. 21 (6), 1487–1524. https://doi.org/10.3233/IDA-163 (2017).
Ciloglugil, B. & Inceoglu, M. M. User Modeling for Adaptive E-Learning Systems, in Computational Science and Its Applications – ICCSA 2012, (eds Murgante, B. et al.) Berlin, Heidelberg: Springer, 550–561 https://doi.org/10.1007/978-3-642-31137-6_42. (2012).
Ali, W., Zhou, X. & Shao, J. Privacy-preserved and responsible recommenders: From conventional defense to federated learning and blockchain. ACM Comput. Surveys. 57 (5), 1–35 (2025).
Umer, K., Zhou, X., Shao, J., Ali, W. & Hidattack: An effective and undetectable model poisoning attack to federated recommenders (IEEE Transactions on Knowledge and Data Engineering, 2024).
Ali, W., Ammad-Ud-Din, M., Zhou, X., Zhang, Y. & Shao, J. Communication-efficient federated neural collaborative filtering with multi-armed bandits. ACM Trans. Recommender Syst. 4 (1), 1–28 (2025).
Kumar, R., Zhou, X., Shao, J., Ali, W. & Responsible recommendation services with blockchain empowered asynchronous federated learning. ACM Trans. Intell. Syst. Technol. 15 (4), 1–24 (2024).
Wang, Y., Xu, H., Ali, W., Zhou, X. & Shao, J. Bilateral Improvement in Local Personalization and Global Generalization in Federated Learning. IEEE Internet Things J. 11 (16), 27099–27111 (2024).
Ali, W., Kumar, J. & Shao, J. Inferring context with reliable collaborators: a novel similarity estimation method for recommender systems. Appl. Intell. 52 (12), 13883–13901 (2022).
Ma, W., Wu, J., Song, D., Chen, Z., & Huang, T. (2026). HVAE-DC: A hierarchical variational autoencoder-based deep clustering model for multi-level driving behavior. Expert Systems with Applications, 305, 130882. doi: https://doi.org/10.1016/j.eswa.2025.130882
edX Courses Dataset. Available: https://www.kaggle.com/datasets/khusheekapoor/edx-courses-dataset-2021 (2021).
Li, Y., He, J., Chen, X., Wang, Z., Chen, Z., Niu, Q.,... Yin, Y. (2026). AugMMRev: An LLM-Augmented Multimodal Ranking Model for Personalized Image Material Retrieval. IEEE Transactions on Consumer Electronics, 1. doi: 10.1109/TCE.2026.3652186
Hao, L., Abdipoor, S., Li, Q. & Xu, L. Hybrid graph neural networks with LSTM attention mechanism for recommendation systems in MOOCs, in Proc. 20th IEEE Int. Colloq. Signal Process. Appl. (CSPA), Langkawi, Malaysia, Mar. pp. 1–6, https://doi.org/10.1109/CSPA60979.2024.10525319 (2024).
Funding
The authors received no financial assistance for this work.
Author information
Authors and Affiliations
Contributions
All authors contributed to the conception and design of the study. Shuhua Liu, Guanyu Chen, and Guangxin Han conducted data collecting, modeling, and analysis.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval
Not relevant.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Chen, G., Han, G. & Liu, S. Context-aware sequential course recommendation via conditional variational autoencoders and transformer architectures in IoT-enabled E-learning systems. Sci Rep (2026). https://doi.org/10.1038/s41598-026-45764-y
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-45764-y
