Federated Learning Setting for E-Learning Course Recommendations

Keywords:
Federated Learning, E-learning, Personalized Learning

Abstract:
The main research problems addressed in this article refer to the complexity of maintaining Learning Management Systems, ensuring data privacy throughout any analysis of that data, and personalizing learning, which can be a task requiring significant resources. The research aims to provide an answer that can address these problems through a Federated Learning setting, enabling cross-institutional cooperation and retaining the data in its place of origin. The research includes a simulation of such a Federated learning setting, which proved to be very interesting for identifying future challenges and directions for a tangible, real-world application. The simulation was built with a dataset comprised of students’ grades and interests in a first-year mandatory subject, E-business, taught at the University of Belgrade, Faculty of Organizational Sciences. This dataset was suitable for building a recommender system that can produce an intelligent suggestion for an elective course for each student individually based on their interests and academic achievements.

CITATION:

IEEE format

Copy to clipboard

M. Jolović, D. Kostić, A. Joksimović, T. Tahirović, P. Lukovac, “Federated Learning Setting for E-Learning Course Recommendations,” in Sinteza 2025 - International Scientific Conference on Information Technology, Computer Science, and Data Science, Belgrade, Singidunum University, Serbia, 2025, pp. 35-40. doi:10.15308/Sinteza-2025-35-40

APA format

Copy to clipboard

Jolović, M., Kostić, D., Joksimović, A., Tahirović, T., Lukovac, P. (2025). Federated Learning Setting for E-Learning Course Recommendations. Paper presented at Sinteza 2025 - International Scientific Conference on Information Technology, Computer Science, and Data Science. doi:10.15308/Sinteza-2025-35-40

BibTeX format
Download

RefWorks Tagged format
Download