Optimizing E-Library Engagement with Hybrid Recommender System

Abstract

With growing reliance on digital libraries, personalized recommendation systems have become essential for enhancing user experience and resource accessibility. This study presents a hybrid recommender model designed to optimize e-library engagement among university students by providing tailored book suggestions based on user preferences and activity patterns. The model integrates Cosine Similarity and Term Frequency-Inverse Document Frequency (TF-IDF) to enhance the accuracy and relevance of recommendations. The system was developed using Python with Django framework for backend and JavaScript with the React framework for the frontend interface. To assess its effectiveness, a structured questionnaire was distributed via Google Forms to 120 randomly selected students, evaluating key performance indicators such as recommendation accuracy, usability, and overall user satisfaction. Experimental results indicate that the model achieved a 95% accuracy rate in recommendations, with participants expressing high satisfaction regarding its precision and ease of use. These findings underscore the significance of hybrid recommender systems in advancing e-library accessibility, promoting user engagement, and facilitating seamless knowledge discovery.