Music recommendation system using emotion triggering low-level features

Recently, many researches of modeling or measuring human feeling have been conducted to understand human emotions. However, researches on music-related human emotions have much difficulty due to the subjective perception of emotions. We selected low-level musical features which may trigger human emotions, based on TV music program´s audience rating information and the corresponding music. In this program, audience was requested to rate music of the contestants and to select their preferred music based on their emotional feelings. In addition, we implemented personalized music recommendation system using selected features, context information and listening history. In the experimental results, we confirmed that selected features can be reliable features when these features are used in music recommendation systems.