PL Framework Guideline for ODL [Webtoolkit]

These involve technologies that provide analytical capabilities to generate meaningful insights that inform personalisation. They include:

• Learning analytics – are technologies that can used in learning management systems to support personalised learning. These technologies provide personalised feedback, assessment, and support to enhance online learning experiences, including data visualisation and learner tracking. Learning Management Systems (LMS) such as Blackboard and Moodle collect data on student interactions, personal information, academic performance, and system usage. By utilising such data, Learning analytics helps educators understand students’ needs such as thier behaviours, preferences, and learning habits, enabling the delivery of personalised learning experiences that can improve student engagement and academic performance.
• Data analytical tools – these are tools used to analyse large datasets and generate meaningful insights. These may include plugins integrated into learning platforms or standalone tools such as Tableau and Power BI.

Resources

• The Role of Learning Analytics in Personalizing Education
• Data-Driven Learning: How Analytics and Gamification Are Personalizing Education

References

• Lluch Molins, L., & Cano Garcia, E. (2023). How to embed SRL in online learning settings? Design through learning analytics and personalized learning design in Moodle. Journal of New Approaches in Educational Research, 12(1), 120–138. http://dx.doi.org/10.7821/naer.2023.1.1127
• Knobbout, J., & Van Der Stappen, E. (2020). Where is the learning in learning analytics? A systematic literature review on the operationalization of learning-related constructs in learning analytics interventions. IEEE Transactions on Learning Technologies, 13(3), 631–645.
• Rodríguez‐Martínez, J. A., González‐Calero, J. A., del Olmo‐Muñoz, J., Arnau, D., & Tirado‐Olivares, S. (2023). Building personalised homework from learning analytics-based formative assessment: Effect on fifth-grade students’ understanding of fractions. British Journal of Educational Technology, 54(1), 76–97.
• Aljohani, N. R., & Davis, H. C. (2013). Learning analytics and formative assessment to provide immediate detailed feedback using a student-centred mobile dashboard. In 2013 Seventh International Conference on Next Generation Mobile Apps, Services and Technologies (pp. 262–267).
• Bittencourt, I. I., & Lemos, W. (2018). Visualizing learning analytics. Springer International Publishing.
• Maseleno, A., Sabani, N., Huda, M., Ahmad, R., Jasmi, K. A., & Basiron, B. (2018). Demystifying learning analytics in personalised learning. International Journal of Engineering & Technology, 7(3), 1124–1129.
• Dietz-Uhler, B., & Hurn, J. E. (2013). Using learning analytics to predict (and improve) student success: A faculty perspective. Journal of Interactive Online Learning, 12(1), 17–26.

Data mining involves the extraction of data that can be reprocessed to support personalised learning tailored to the educational experiences of individual learners. It includes capturing data from learning platforms such as adaptive e-learning systems, user logs, access path analysis, and browsing behaviour. The main goal is to analyse and predict learner needs in order to provide personalised support and guidance, as well as improve learning outcomes. Data mining enables the identification of patterns and student behaviours, detection of knowledge gaps, prediction of student performance, creation of customised learning paths, and adaptation of content to meet individual learner needs.

Data Mining Techniques Used

• K-means clustering
• Classification (e.g., decision trees)
• Association rule mining
• Regression analysis
• Sequential pattern mining
• Sentiment analysis

References

• Cai, J., & Li, Y. (2024). Fuzzy association rule mining for personalized English language teaching from higher education. Journal of Computational Methods in Sciences and Engineering, 24(6), 3617–3631.
• Daghestani, L. F., Ibrahim, L. F., Al-Towirgi, R. S., & Salman, H. A. (2020). Adapting gamified learning systems using educational data mining techniques. Computer Applications in Engineering Education, 28(3), 568–589.
• Dwivedi, D. N., Mahanty, G., & Dwivedi, V. (2024). The role of predictive analytics in personalizing education: Tailoring learning paths for individual student success. In Enhancing education with intelligent systems and data-driven instruction (pp. 44–59). IGI Global Scientific Publishing.
• Li, D. (2024). Creating personalized higher education teaching system using fuzzy association rule mining. International Journal of Computational Intelligence Systems, 17(1), 239.
• Lin, C. F., Yeh, Y. C., Hung, Y. H., & Chang, R. I. (2013). Data mining for providing a personalized learning path in creativity: An application of decision trees. Computers & Education, 68, 199–210.
• Manjarres, A. V., Sandoval, L. G. M., & Suárez, M. S. (2018). Data mining techniques applied in educational environments: Literature review. Digital Education Review, (33), 235–266.
• Villegas-Ch, W., & Luján-Mora, S. (2017). Analysis of data mining techniques applied to LMS for personalized education. In 2017 IEEE World Engineering Education Conference (EDUNINE) (pp. 85–89). IEEE.
• Wu, S., Cao, Y., Cui, J., Li, R., Qian, H., Jiang, B., & Zhang, W. (2024). A comprehensive exploration of personalized learning in smart education: From student modeling to personalized recommendations. arXiv preprint arXiv:2402.01666.

Machine learning methods and algorithms enable the development of intelligent personalised learning environments based on learner needs. These algorithms analyse user data, such as behaviour and preferences, to identify needs and deliver personalised services. They generate predictive models that support decision-making in new learning situations.

Machine learning algorithms are used to process collected data and support personalisation features such as prediction, classification, and recommendation. Common techniques include:

• Supervised learning – decision trees, SVM, K-NN, logistic regression, random forest, naïve Bayes
• Unsupervised learning – clustering, association rules, dimensionality reduction
• Reinforcement learning – Q-learning, SARSA, DQN
• Semi-supervised learning – e.g. GAN-based approaches