an Interpretable Sequence Modeling of Educational Behavior using Temporal Attention Networks
DOI:
https://doi.org/10.26713/cma.v17i1.3339Abstract
The increasing popularity of learning platforms online has led to vast amounts of sequential data regarding learner behavior. Available predictive models tend to focus on fixed features. They cannot pinpoint the time-dynamic changes in learning activity, which reduces the effectiveness of predictive methods and makes them more difficult to understand. In this work, the Dynamic Temporal Attention Network (DTAN) is proposed. This novel deep learning architecture learns e-learning behavior based on time-aware attention and temporal convolution to enhance the predictive accuracy and interpretability. TCN has already been combined with two significant attention modules. The Attention-over-Time windows (ATW) and the Dynamic Contextual Attention Mechanism (DCAM). With such components, the model can learn short and long-term dependencies on the learner behavior and adaptively prioritize critical time slots. To train and evaluate the model, two large-scale datasets are used: EdNet, containing over 130 million question-and-answer interactions in the K-12 context, and OULAD, an exam-taking dataset in the university context. By outperforming state-of-the-art models, including long-short term memory (LSTM) and gated recurrent units (GRU), and standard TCNs, TAN results in a significant improvement in diverse classification tasks. It has a strong early prediction skill and an interpretable visualization that focuses on weight, marking critical incidences of a growing learner journey. Such observations are essential in the process of providing individual instruction and necessary intervention. TAN delivers a solution to sequential data modeling in education that is interpretable, thereby boosting efficiency significantly, mainly when used in adaptive learning systems.
Downloads
References
C. Romero and S. Ventura, "Educational data mining and learning analytics: An updated survey," Wiley interdisciplinary reviews: Data mining and knowledge discovery, vol. 10, p. e1355, 2020.
B. Alnasyan, M. Basheri, and M. Alassafi, "A Comprehensive Comparative Analysis of Deep Learning Models for Student Performance Prediction in Virtual Learning Environments: Leveraging the OULA Dataset and Advanced Resampling Techniques," IEEE Access, 2025.
T. Xie, Q. Zheng, and W. Zhang, "Mining temporal characteristics of behaviors from interval events in e-learning," Information Sciences, vol. 447, pp. 169-185, 2018.
C. Piech, J. Bassen, J. Huang, S. Ganguli, M. Sahami, L. J. Guibas, et al., "Deep knowledge tracing," Advances in neural information processing systems, vol. 28, 2015.
S. Bai, J. Z. Kolter, and V. Koltun, "An empirical evaluation of generic convolutional and recurrent networks for sequence modeling," arXiv preprint arXiv:1803.01271, 2018.
S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural computation, vol. 9, pp. 1735-1780, 1997.
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, et al., "Attention is all you need," Advances in neural information processing systems, vol. 30, 2017.
K. R. Koedinger, S. D'Mello, E. A. McLaughlin, Z. A. Pardos, and C. P. Rosé, "Data mining and education," Wiley Interdisciplinary Reviews: Cognitive Science, vol. 6, pp. 333-353, 2015.
Y. Zhou and J. Kang, "Enriching Multimodal Data: A Temporal Approach to Contextualize Joint Attention in Collaborative Problem-Solving," Journal of Learning Analytics, vol. 10, pp. 87-101, 2023.
A. Peña-Ayala, "Educational data mining: A survey and a data mining-based analysis of recent works," Expert systems with applications, vol. 41, pp. 1432-1462, 2014.
A. T. Corbett and J. R. Anderson, "Knowledge tracing: Modeling the acquisition of procedural knowledge," User modeling and user-adapted interaction, vol. 4, pp. 253-278, 1994.
K. Cho, B. Van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, et al., "Learning phrase representations using RNN encoder-decoder for statistical machine translation," arXiv preprint arXiv:1406.1078, 2014.
B. Lim and S. Zohren, "Time-series forecasting with deep learning: a survey," Philosophical Transactions of the Royal Society A, vol. 379, p. 20200209, 2021.
B. Shickel, P. J. Tighe, A. Bihorac, and P. Rashidi, "Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR) analysis," IEEE journal of biomedical and health informatics, vol. 22, pp. 1589-1604, 2017.
L. He, X. Li, P. Wang, J. Tang, and T. Wang, "MAN: Memory-augmented attentive networks for deep learning-based knowledge tracing," ACM Transactions on Information Systems, vol. 42, pp. 1-22, 2023.
S. Pandey and G. Karypis, "A self-attentive model for knowledge tracing," arXiv preprint arXiv:1907.06837, 2019.
D. Shin, Y. Shim, H. Yu, S. Lee, B. Kim, and Y. Choi, "Saint+: Integrating temporal features for ednet correctness prediction," in LAK21: 11th International Learning Analytics and Knowledge Conference, 2021, pp. 490-496.
S. Alqahtani, "Leveraging Techniques of Epistemic Network Analysis to Discover Behaviors of Student Learning Reflections in Online Learning Environments," Engineering, Technology & Applied Science Research, vol. 14, pp. 14191-14199, 2024.
A. A. Mir, M. F. Zuhairi, S. Musa, F. Alanazi, A. Namoun, and A. Alrehaili, "Enhanced Variational Graph Convolutional Networks with Multi-Scale Convolutions and Attention Mechanisms for Dynamic Network Analysis," Engineering, Technology & Applied Science Research, vol. 15, pp. 19838-19847, 2025.
S. Ghaoui, S. M. Hemam, and T. Djouad, "An MDA-based Approach for the Design and Automatic Computation of Collaboration Indicators in E-Learning Systems," Engineering, Technology & Applied Science Research, vol. 15, pp. 23235-23245, 2025.
D. Shin and S. Lee, "EdNet," Github, Ed., ed, 2020.
M. H. Jakub Kuzilek, Zdenek Zdrahal, "Open University Learning Analytics Dataset,," S. Data, Ed., ed, 2017.
C. Piech, J. Bassen, J. Huang, S. Ganguli, M. Sahami, L. Guibas, et al., "Deep knowledge tracing. Advances in neural information processing systems," Association for Computing Machinery, pp. 201-204, 2015.
J. Zhang, X. Shi, I. King, and D.-Y. Yeung, "Dynamic key-value memory networks for knowledge tracing," in Proceedings of the 26th international conference on World Wide Web, 2017, pp. 765-774.
T. Gervet, K. Koedinger, J. Schneider, and T. Mitchell, "When is deep learning the best approach to knowledge tracing?," Journal of Educational Data Mining, vol. 12, pp. 31-54, 2020.
Published
Issue
Section
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a CCAL that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
