Collaborative Recommendation Systems for E-Learning Sources
M. Maheswari, Ms. B Bala Sai Gayathri, Mopuru Yoshna Reddy, S. L. Jany Shabu, J. Refonaa, Dhamodaran · 2025
The era of digital learning necessitates personalized recommendations for effective educational experiences. This study presents a Collaborative Recommendation System for E-Learning Sources, leveraging collaborative filtering based on user reviews, completion data, and preferences. A hybrid approach integrating user-based and item-based filtering, matrix factorization, and deep learning addresses sparsity and cold-start issues while maintaining scalability and privacy. Experimental evaluations on multiple benchmark datasets demonstrate improved learning engagement, with a 92% user satisfaction rate, enhanced recommendation diversity, and a 30% increase in platform engagement. The model was implemented using Google Colab with TensorFlow and PyTorch, with a learning rate of 0.001, 50 epochs, and a batch size of 64. These findings indicate the system's efficacy in personalizing e-learning environments.