A Context-Aware Hybrid Recommendation Framework for E-Learning Platforms

Abstract: E-learning platforms provide learners with ex-tensive digital resources that enable self-paced and location-independent study. However, the overwhelming volume of learning materials offered by a wide range of institutions and content providers makes personalized guidance increasingly essential for effective knowledge acquisition. As a result, recommender systems have become fundamental components of modern e-learning environments, helping to reduce information overload and support individualized learning experiences. In general, the richer and more diverse the available data, the more accurate and relevant the resulting recommendations. Despite these advantages, conventional recommendation approaches often fail to fully exploit the contextual and relational information inherent in e-learning ecosystems, which limits their adaptability and predictive precision. This study proposes a hybrid recommendation framework that integrates collaborative filtering, content-based filtering, and context-aware modeling to generate more accurate and adaptive course recommendations. The proposed system infers learner preferences by combining historical interaction data, contextual attributes, and course characteristics, while also incorporating temporal and environmental factors that influence learning behavior. Experimental evaluations based on SVD, TF-IDF, and RNN models applied to a well-established benchmark dataset demonstrate that the proposed hybrid framework significantly improves recommendation accuracy, coverage, and adaptability compared with baseline methods. Furthermore, the integration of contextual information effectively alleviates the cold-start problem and better captures learners’ evolving goals and learning trajectories. Overall, the results confirm that combining multiple recommendation paradigms within e-learning platforms enables more adaptive, personalized, and scalable learning pathways, making the proposed system suitable for diverse educational contexts and learner profiles.

Kaoutar Errakha, Amina Samih, Sanaa Dfouf and Abderrahim Marzouk. “A Context-Aware Hybrid Recommendation Framework for E-Learning Platforms”. International Journal of Advanced Computer Science and Applications (IJACSA) 17.2 (2026). http://dx.doi.org/10.14569/IJACSA.2026.0170279

@article{Errakha2026,
title = {A Context-Aware Hybrid Recommendation Framework for E-Learning Platforms},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2026.0170279},
url = {http://dx.doi.org/10.14569/IJACSA.2026.0170279},
year = {2026},
publisher = {The Science and Information Organization},
volume = {17},
number = {2},
author = {Kaoutar Errakha and Amina Samih and Sanaa Dfouf and Abderrahim Marzouk}
}