MOVIE RECOMMENDATION SYSTEM USING FACIAL EMOTIONS
Abstract
Abstract
In today’s digital world, people have access to thousands of movies online, making it difficult to decide which one to watch. Traditional movie recommendation systems mostly depend on users’ past ratings or viewing history, which may not always reflect their current mood or emotions. This project focuses on developing a movie recommendation system that uses facial emotion detection and recognition to suggest movies that match how a user feels at the moment. The system makes use of FaceAPI.js and TensorFlow.js for real-time facial emotion analysis through a webcam, detecting emotions such as happiness, sadness, anger, or surprise. Each detected emotion is linked to specific movie genres to give a more personalized recommendation. The project was implemented using PHP, JavaScript, and the FER2013 dataset for model training. The results show that combining emotion detection with movie recommendation improves the accuracy and relevance of suggested movies compared to traditional methods. This study demonstrates that emotion-aware systems can greatly improve user experience and satisfaction in online entertainment platforms.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.