Abstract:
"This study aimed to develop a hybrid movie recommendation system by integrating emotion detection and merging
collaborative and content-based filtering techniques, significantly enhancing personalization by aligning movie
suggestions with users' current emotional states. This innovative approach addresses the cold start problem and data
sparsity effectively, utilizing Convolutional Neural Networks (CNNs) for accurate emotion recognition from facial
expressions. Evaluation results indicate improved accuracy and user satisfaction, confirming that the integration of
emotional alignment and merged filtering techniques increases engagement and relevancy of recommendations
Future enhancements could nclude expanding the emotion dataset, refining adaptability across demographics, and
integrating contextual factors to further implove recommendation precision. This study contributes to the advancement
of recommendation systems and sets the stage for future research in emotion-based user interfaces, highlighting the
potential for more empathetic and responsive entertainment technologies. "
