Development of an ALS-Based Collaborative Filtering Model for Authentic Learning Recommendations in Moodle
DOI:
https://doi.org/10.37253/joint.v7i1.12618Keywords:
Collaborative Filtering, Skill Authenticity, Personalized Learning, Moodle, ALSAbstract
Personalized learning recommendations in Learning Management Systems (LMS) often rely on learner interaction patterns but may not adequately address competency gaps and authentic skill development. This study proposes ACTS-CF (Authenticity-aware Collaborative Filtering), a recommendation model that integrates Moodle learner interaction data, implicit feedback, Alternating Least Squares (ALS), and Skill Authenticity-based competency gap analysis. Moodle learning activities are transformed into learner–item interactions, and implicit ALS is used to generate candidate recommendations. These recommendations are then refined using learners’ Skill Authenticity deficiencies to prioritize learning activities that support authentic skill development. The model was evaluated against baseline ALS using Precision@5, Recall@5, and Normalized Discounted Cumulative Gain (NDCG@5). ACTS-CF achieved the same Precision@5 (0.4667) and Recall@5 (0.3525) as ALS, while improving NDCG@5 from 0.5130 to 0.5530. The findings indicate that integrating Skill Authenticity into collaborative filtering can improve recommendation ranking while maintaining retrieval effectiveness, providing a more competency-aware approach to personalized learning in Moodle.
Downloads
References
P. Ngulube and M. M. Ncube, “Leveraging Learning Analytics to Improve the User Experience of Learning Management Systems in Higher Education Institutions,” Inf., vol. 16, no. 5, p. 419, 2025, doi: 10.3390/info16050419.
A. Silvola, P. Näykki, A. Kaveri, and H. Muukkonen, “Expectations for supporting student engagement with learning analytics: An academic path perspective,” Comput. Educ., vol. 168, 2021, doi: 10.1016/j.compedu.2021.104192.
V. A. Nguyen, H. H. Nguyen, D. L. Nguyen, and M. D. Le, “A course recommendation model for students based on learning outcome,” Educ. Inf. Technol., vol. 26, no. 5, pp. 5389–5415, 2021, doi: 10.1007/s10639-021-10524-0.
K. Naji and A. Ibriz, “Approach for Eliciting Learners’ Preferences in Moocs Through Collaborative Filtering,” Int. J. Emerg. Technol. Learn., vol. 17, no. 14, pp. 235–245, 2022, doi: 10.3991/ijet.v17i14.29887.
D. F. Murad, Y. Heryadi, S. M. Isa, and W. Budiharto, “Personalization of study material based on predicted final grades using multi-criteria user-collaborative filtering recommender system,” Educ. Inf. Technol., vol. 25, no. 6, pp. 5655–5668, 2020, doi: 10.1007/s10639-020-10238-9.
D. F. Murad, S. A. Murad, and M. Irsan, “the Effect of Contextual Information As an Additional Feature in the Recommendation System,” J. Educ. Online, vol. 20, no. 1, 2023, doi: 10.9743/JEO.2023.20.1.10.
J. Herrington and R. Oliver, “An instructional design framework for authentic learning environments,” Educ. Technol. Res. Dev., vol. 48, no. 3, pp. 23–48, 2000, doi: 10.1007/BF02319856.
J. T. M. Gulikers, T. J. Bostiaens, and P. A. Kirschner, “A five-dimensional framework for authentic assessment,” Educ. Technol. Res. Dev., vol. 52, no. 3, pp. 67–86, Mar. 2004, doi: 10.1007/BF02504676.
J. H. Lee, S. Campbell, M. K. Choi, and J. Bae, “Authentic learning in heathcare education: A systematic review,” Nurse Educ. Today, vol. 119, p. 105596, 2022, doi: 10.1016/j.nedt.2022.105596.
L. Guo, H. Jiang, X. Wang, and F. Liu, “Learning to recommend point-of-interest with the weighted Bayesian personalized ranking method in LBSNs,” Inf., vol. 8, no. 1, p. 20, 2017, doi: 10.3390/info8010020.
H. J. Watson et al., “The CRISP-DM Model: The New Blueprint for Data Mining,” J. Data Warehous., vol. 5, no. 4, pp. 15–18, 2000.
Y. Hu, C. Volinsky, and Y. Koren, “Collaborative filtering for implicit feedback datasets,” in Proceedings - IEEE International Conference on Data Mining, ICDM, 2008, pp. 263–272. doi: 10.1109/ICDM.2008.22.
F. L. da Silva et al., “A systematic literature review on educational recommender systems for teaching and learning: research trends, limitations and opportunities,” Educ. Inf. Technol., vol. 28, no. 3, pp. 3289–3328, 2023, doi: 10.1007/s10639-022-11341-9.
G. M. Dhananjaya, R. H. Goudar, A. A. Kulkarni, V. N. Rathod, and G. S. Hukkeri, “A Digital Recommendation System for Personalized Learning to Enhance Online Education: A Review,” IEEE Access, vol. 12, pp. 34019–34041, 2024, doi: 10.1109/ACCESS.2024.3369901.
M. Deschênes, “Recommender systems to support learners’ Agency in a Learning Context: a systematic review,” Int. J. Educ. Technol. High. Educ., vol. 17, no. 1, p. 50, 2020, doi: 10.1186/s41239-020-00219-w.
J. M. Helm et al., “Machine Learning and Artificial Intelligence: Definitions, Applications, and Future Directions,” Curr. Rev. Musculoskelet. Med., vol. 13, no. 1, pp. 69–76, 2020, doi: 10.1007/s12178-020-09600-8.
.png){kind=small}
