Real-Time Music Recommendation System Using Facial Emotion Recognition

This research proposes a novel approach for music recommendation systems based on facial expression analysis to provide personalized recommendations. In an attempt to recommend music appropriate to the mood of the user, the system examines the user's facial expressions through machine learning algorithms to determine their emotional state. The proposed system employs a collaborative filtering algorithm to generate personalized music recommendations and a deep learning-based model to recognize and classify facial emotions. Participant ratings for their favorite music and images of their facial expressions were used to evaluate the proposed approach. The results indicate that the proposed system can accurately forecast the emotional state of the user and provide personalized music recommendations suitable for their mood. This study suggests a new method for music recommendation systems that uses facial expression analysis to offer tailored suggestions. In order to suggest music that fits the user's mood, the system analyzes their facial expressions using machine learning algorithms to ascertain their emotional state. The suggested system uses a collaborative filtering algorithm to produce tailored music recommendations and a deep learning-based model to identify and categorize facial emotions. A dataset of participant ratings for their preferred music and photos of their facial expressions was used to assess the suggested approach. The findings show that the suggested system is capable of precisely predicting the user's emotional state and offering tailored music suggestions that are appropriate for their mood. Additionally, this would enable the recovery of labor and time spent physically carrying out the process on a larger scale. The main objective of the system is to identify face emotions and make music recommendations fast. With the suggested system, time and money will be saved.