An Intelligent Hybrid Recommendation System for E-Learning Personalization in Smart Campus

The rapid evolution of digital education has necessitated intelligent, scalable systems capable of personalizing learning experiences in smart campus environments. This paper proposes a hybrid recommendation framework that integrates content-based filtering and collaborative filtering to deliver accurate and context-aware course recommendations. The system leverages a real-world e-learning dataset enriched with textual features and user interaction simulations to create a robust recommendation engine. Text preprocessing and TF-IDF vectorization capture semantic content, while user-course enrollment patterns support behavioral modeling via cosine similarity. A hybrid scoring mechanism fuses both sources of information, with evaluation conducted through six-fold cross-validation using Precision@K and Recall@K met- rics. The hybrid model consistently outperforms baseline methods, achieving perfect recall and the highest precision across all top-K thresholds. Case studies further demonstrate the model’s ability to generate relevant, diverse, and personalized course suggestions, validating its potential to enhance learner engagement and satisfaction. This study contributes an interpretable and scalable solution for adaptive e-learning personalization within smart educational ecosystems.