An emotion model for music using brain waves

Every person reacts differently to music. The task then is to identify a specific set of music features that have a significant effect on emotion for an individual. Previous research have used self-reported emotions or tags to annotate short segments of music using discrete labels. Our approach uses an electroencephalograph to record the subject\u27s reaction to music. Emotion spectrum analysis method is used to analyze the electric potentials and provide continuous-valued annotations of four emotional states for different segments of the music. Music features are obtained by processing music information from the MIDI files which are separated into several segments using a windowing technique. The music features extracted are used in two separate supervised classification algorithms to build the emotion models. Classifiers have a minimum error rate of 5% predicting the emotion labels. © 2012 International Society for Music Information Retrieval