Music mood classification model based on arousal-valence values

This paper presents a music mood classification model based on arousal-valence (AV) values for music recommendation system. We analyse the collected music mood tags and AV values from 10 subjects and classify music mood on the AV plane into 8 regions by using k-means clustering algorithm. For each region, we propose representative mood tags by using statistics. We find that some regions can be identified by representative mood tags like previous models but some mood tags are overlapped in almost regions. The proposed model can express a region with several representative moods and a mood distributed uniformly in almost regions.