Thai music emotion recognition by linear regression

Abstract

Music emotion recognition has rapidly grown in the present because the listener’s behavior is changing. Therefore, music emotion recognition helps to understand the emotion of music, listener, and support many careers in the music industry including general people. Many researchers have studied western music, but a few studied Thai music. In this work, we are interested to use 155 popular Thai music for explore emotion and use valence-arousal(energy) values from Spotify API to investigate the results. We select multiple linear regression (MLR) and support vector regression (SVR), kinds of ‘Linear’ function for valence-arousal values prediction. Experimental results demonstrate that the multiple linear regression provides highest accuracy (61.29%), precision (65%), recall (61%) and f-measure (60%) which is more than support vector regression.