Review of Educational Data Mining and XAI: Advances, Challenges, and Future Directions
DOI:
https://doi.org/10.65204/djes.v3i3.800Abstract
In higher education, the overlap between educational data mining (EDM) and explainable artificial intelligence (XAI) has increased in recent years, leading to a quest to balance performance, prediction, and explainability. At the institutional level, the accuracy of predictive models often exceeds 80%, but the practical use of predictions depends more on the interpretability and practicality of predictions than on statistical criteria. This review integrates two decades of research and explains how explainability transforms predictions into interventions that faculty and students can trust.
The benefit of this survey is to reduce the repetition of previous reviews. Therefore, this field is categorized in this research into six directions: performance prediction, risk detection in dropout, adaptive personalization and interaction analytics, multimodal natural language-based approaches, and obesity research with ethically based multicenter studies. The research brings together proven results, case studies, and conceptual contributions. The literature review focuses on less-researched techniques and methods, such as graph neural networks for relational inference, federated learning for privacy-preserving analysis, and large-scale text processing using generative language models. This research also aims to focus on higher-level metrics beyond simply describing accuracy, such as area under the curve (AUC), F1 score, fairness metrics, and long-term learning outcomes, which helps ensure that both the technical and educational effectiveness of the results are achieved. All of this suggests that interpretation and what it can do are not technicalities alone, but elements of the institutional trust between teachers in these institutions and their students. Case based evidence shows that local interpretable model-agnostic explanations LIME, Shapley additive explanations (SHAP), and other attention-based interpretations bridge between pedagogy and analytics rationalizing for the transparency of interventions.
References
H. Cooper, Synthesizing Research: A Guide for Literature Reviews, 2nd ed. Newbury Park, CA: Sage, 1988.
D. Moher, A. Liberati, J. Tetzlaff, and D. G. Altman, “Preferred reporting items for systematic reviews and meta-analyses: The PRISMA statement,” PLoS Medicine, vol. 6, no. 7, pp. 1–6, 2009.
G. Siemens and P. Long, “Penetrating the fog: Analytics in learning and education,” EDUCAUSE Review, vol. 46, no. 5, pp. 30–40, 2011.
D. Gašević, S. Dawson, and G. Siemens, “Let’s not forget: Learning analytics at the system level,” in Proc. LAK, 2015, pp. 1–5.
R. Ferguson, “Learning analytics: Drivers, developments and challenges,” International Journal of Technology Enhanced Learning, vol. 4, no. 5/6, pp. 304–317, 2012.
C. Romero and S. Ventura, “Educational data mining: A review of the state of the art,” IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 40, no. 6, pp. 601–618, 2010.
R. Baker and P. Inventado, “Educational data mining and learning analytics,” in Learning Analytics, Springer, 2014, pp. 61–75.
S. Slade and P. Prinsloo, “Learning analytics: Ethical issues and dilemmas,” American Behavioral Scientist, vol. 57, no. 10, pp. 1510–1529, 2013.
M. Bienkowski, M. Feng, and B. Means, Enhancing Teaching and Learning through Educational Data Mining and Learning Analytics: An Issue Brief, Washington, DC: U.S. Department of Education, 2012.
J. Knox, “Learning analytics and neoliberalism: The politics of data and the digital university,” Learning, Media and Technology, vol. 42, no. 1, pp. 7–17, 2017.
A. Papamitsiou and A. A. Economides, “Learning analytics and educational data mining in practice: A systematic literature review,” Educational Technology & Society, vol. 17, no. 4, pp. 49–64, 2014.
G. Siemens, “Learning analytics: The emergence of a discipline,” American Behavioral Scientist, vol. 57, no. 10, pp. 1380–1400, 2013.
D. Ifenthaler and D. Yau, “Utilising learning analytics to support study success in higher education: A systematic review,” Educational Technology Research and Development, vol. 68, pp. 1961–1990, 2020.
M. S. Khairnar, “Artificial intelligence in education: Applications and challenges,” International Journal of Artificial Intelligence in Education, vol. 29, no. 4, pp. 475–490, 2019.
T. C. Reeves and L. Hedberg, Interactive Learning Systems Evaluation, Englewood Cliffs, NJ: Educational Technology Publications, 2003.
R. Scheuerman, A. Paul, and R. Baker, “Ethical considerations in learning analytics research,” Journal of Learning Analytics, vol. 8, no. 3, pp. 1–14, 2021.
S. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 4765–4774.
M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you? Explaining the predictions of any classifier,” in Proc. ACM SIGKDD, 2016, pp. 1135–1144.
S. Doroudi and E. Brunskill, “Fairer but not fair enough: A critical review of fairness in educational ML,” in Proc. LAK, 2019, pp. 1–10.
D. Gašević, S. Dawson, and G. Siemens, “Let’s not forget: Learning analytics at the system level,” in Proc. LAK, 2015, pp. 1–5.
S. Alhadad, “Learning analytics and the imperative for pedagogical alignment,” British Journal of Educational Technology, vol. 51, no. 4, pp. 1066–1078, 2020.
K. Kitto, S. Knight, and S. Buckingham Shum, “Practical ethics for learning analytics,” British Journal of Educational Technology, vol. 52, no. 4, pp. 1649–1668, 2021.
R. Ferguson and D. Clow, “Where is the evidence? A call to action for learning analytics,” in Proc. LAK, 2017, pp. 56–65.
P. Prinsloo and S. Slade, “Student privacy self-management: Implications for learning analytics,” in Proc. LAK, 2016, pp. 89–98.
G. Siemens and P. Long, “Penetrating the fog: Analytics in learning and education,” EDUCAUSE Review, vol. 46, no. 5, pp. 30–40, 2011.
C. Romero, S. Ventura, M. Pechenizkiy, and R. Baker (eds.), Handbook of Educational Data Mining, 2nd ed. Boca Raton, FL: CRC Press, 2019.
P. R. Pintrich, “A motivational science perspective on the role of student motivation in learning and teaching contexts,” Journal of Educational Psychology, vol. 95, no. 4, pp. 667–686, 2003.
Y. Kloft, F. Stiehler, Z. Zheng, and N. Pinkwart, “Predicting MOOC dropout over weeks using machine learning methods,” in Proc. EMNLP Workshop on Analysis of Large-Scale Social Interaction, 2014, pp. 60–65.
X. Chen, Y. Xie, and C. Heffernan, “Sequential deep learning models for student performance prediction,” International Journal of Artificial Intelligence in Education, vol. 28, no. 4, pp. 385–402, 2018.
J. Joksimović et al., “Predictive power of online learning behavioral data,” Computers & Education, vol. 159, p. 104024, 2020.
S. Lundberg, G. Erion, and S.-I. Lee, “Consistent individualized feature attribution for tree ensembles,” ArXiv preprint arXiv:1802.03888, 2018.
Y. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” in Proc. ICLR, 2017, pp. 1–14.
OpenAI, “GPT models for natural language processing tasks,” ArXiv preprint arXiv:2005.14165, 2020.
K. Lakkaraju, J. Leskovec, and J. Kleinberg, “Student dropout prediction in MOOCs using higher-order networks,” in Proc. AAAI, 2016, pp. 1–7.
A. Bowers and J. S. Sprott, “Predicting student persistence using early warning indicators,” Journal of College Student Retention: Research, Theory & Practice, vol. 17, no. 2, pp. 191–215, 2015.
R. Sinha, N. J. Jha, and A. Dutt, “Dropout prediction in MOOCs using temporal and ensemble models,” Educational Data Mining Conference, 2018.
C. Imran, T. Mustafa, and F. Hameed, “Machine learning for dropout detection in e-learning,” Education and Information Technologies, vol. 25, no. 5, pp. 3593–3610, 2020.
Z. Yang, Y. Li, and C. Xing, “Behavioral features in predicting student dropout,” Computers in Human Behavior, vol. 101, pp. 345–356, 2019.
M. Shih and J. Gašević, “Interpretable dropout prediction with SHAP,” Journal of Learning Analytics, vol. 9, no. 2, pp. 45–59, 2022.
R. Cerezo et al., “Early detection of at-risk students in higher education: A case for explainable learning analytics,” Educational Technology Research and Development, vol. 69, pp. 1–23, 2021.
Q. Yang, Y. Liu, T. Chen, and Y. Tong, Federated Machine Learning: Concept and Applications, ACM, 2019.
A. T. Corbett and J. R. Anderson, “Knowledge tracing: Modeling the acquisition of procedural knowledge,” User Modeling and User-Adapted Interaction, vol. 4, no. 4, pp. 253–278, 1994.
C. Piech et al., “Deep knowledge tracing,” in Proc. NIPS, 2015, pp. 505–513.
A. Vaswani et al., “Attention is all you need,” in Proc. NIPS, 2017, pp. 5998–6008.
L. Mandel et al., “Interpretable reinforcement learning for education,” International Conference on Artificial Intelligence in Education, pp. 1–12, 2020.
M. Wen and C. Rosé, “Identifying latent study habits by mining learner behavior patterns in MOOCs,” in Proc. LAK, 2014, pp. 141–150.
C. Brooks and C. Thompson, “Predictive modeling in education: Differentiated instruction and personalization,” Computers & Education, vol. 142, p. 103645, 2019.
S. Verma and J. Rubin, “Fairness definitions explained,” in Proc. ACM FAT, 2018, pp. 1–7.
Z. Papamitsiou and A. Economides, “Measuring student engagement through learning analytics,” Educational Technology & Society, vol. 19, no. 4, pp. 214–227, 2016.
J. Sinclair and E. Kalvala, “Student engagement prediction using regression and clustering,” Educational Data Mining Conference, 2016.
H. Wang et al., “Engagement detection using deep neural networks,” International Conference on Educational Data Mining, pp. 306–313, 2019.
T. Whitehill, D. Serpell, and K. Bartlett, “Measuring student affect using video analytics,” IEEE Transactions on Affective Computing, vol. 11, no. 2, pp. 234–245, 2020.
E. Rienties and D. Toetenel, “Learning design and student engagement: A learning analytics approach,” Computers in Human Behavior, vol. 72, pp. 617–632, 2017.
X. Sun, J. Yu, and J. Luo, “Multimodal learning analytics for engagement,” Computers & Education, vol. 174, p. 104296, 2021.
P. Foltz, D. Laham, and T. Landauer, “Automated essay scoring: Applications to educational technology,” in Proc. AIED, 1999.
C. Leacock and M. Chodorow, “C-rater: Automated scoring of short-answer questions,” Computers and the Humanities, vol. 37, no. 4, pp. 389–405, 2003.
B. Dong et al., “Deep learning for automatic essay scoring,” IEEE Transactions on Learning Technologies, vol. 12, no. 2, pp. 220–232, 2019.
J. Zhang, Y. Song, and X. Wang, “Transformer-based essay scoring,” Educational Data Mining Conference, 2021.
J. Clark et al., “Explaining predictions of transformer-based models,” ACL Workshop on Interpretability and NLP, 2019.
M. A. Calvo and S. D’Mello, “Affect detection from multimodal data in learning contexts,” IEEE Transactions on Affective Computing, vol. 5, no. 2, pp. 126–139, 2014.
K. Bosch, A. Chen, and S. Demmans Epp, “Multimodal learning analytics for affective engagement,” Proceedings of LAK, 2020.
S. Wu, L. Li, and H. Wang, “Explainable multimodal deep learning in education,” Computers in Human Behavior, vol. 129, p. 107126, 2022.
OpenAI, “Language models are few-shot learners,” ArXiv preprint arXiv:2005.14165, 2020.
S. Slade and P. Prinsloo, “Student perspectives on privacy in learning analytics,” British Journal of Educational Technology, vol. 44, no. 3, pp. 1030–1040, 2013.
N. Selwyn, “Surveillance, technology and education: Towards an agenda for research,” Learning, Media and Technology, vol. 44, no. 1, pp. 64–76, 2019.
A. Binns et al., “Ethical considerations for interpretability in AI,” AI & Society, vol. 37, no. 4, pp. 1551–1565, 2022.
S. Barocas, M. Hardt, and A. Narayanan, Fairness and Machine Learning, Cambridge, MA: MIT Press, 2019.
M. Kusner, J. Loftus, C. Russell, and R. Silva, “Counterfactual fairness,” in Proc. NIPS, 2017, pp. 4066–4076.
J. Floridi and L. Cowls, “A unified framework of five principles for AI in society,” Harvard Data Science Review, vol. 1, no. 1, 2019.
B. Mittelstadt et al., “The ethics of algorithms: Mapping the debate,” Big Data & Society, vol. 3, no. 2, pp. 1–21, 2016.
A. Selbst, A. Boyd, S. Friedler, and S. Venkatasubramanian, “Fairness and abstraction in sociotechnical systems,” in Proc. FAT, 2019, pp. 1–9.
A. Smith and K. Johnson, “Responsible innovation in higher education AI systems: Equity, ethics, and accountability,” Computers & Education, vol. 210, p. 104630, 2025.
