Kid´s song classification based on mood parameters using K-Nearest Neighbor classification method and Self Organizing Map

Music is closely related to human psychology. A piece of music often associated with certain adjectives such as happy, sad, romantic, and so on. The linkage between the music with a certain mood has been widely used in various occasions by people and music classification based on relevance to a particular emotion is important. This research concerns with music classification system based on mood parameters using K-Nearest Neighbor classification method and Self Organizing Map. The mood parameters used is based on Robert Thayer´s energy-stress model which are exuberance / happy, contentment / relax, anxious and depression. Features that are used are rhythm patterns of the music. The system built has additional facility that that can play songs according to mood chosen. The system is tested using a set of kid song and can show the number of clusters and the mood of a song collection. Classification results obtained by the two classification methods, the K-Nearest Neighbor and Self Organizing Map, are compared with the mood obtained by child psychology experts.