Detection of Four Basic Emotions

Abstract

This chapter presents the detection of emotions in music files using the categorical approach. Four emotion classes which correspond to the four quarters of Russell’s emotion model were used. The research process included constructing training data, feature extraction, feature selection, and building classifiers. We selected features and found sets of features that were the most useful for detecting individual emotions. We examined the effect of low-level, rhythm and tonal features on the accuracy of the constructed classifiers. We built classifiers for different combinations of feature sets, which enabled distinguishing the most useful feature sets for individual emotions. The result of emotion tracking in music files are emotion maps, which visualize the distribution of four emotions over time.