Music Genre Classification using Lyric Mining Based ontf-Idf

Abstract

With the advancement in the internet technologies, music domain has flourished with better access to various music libraries. In the present times, we are able to access music files over the internet with ease. Nowadays, the lyrics sets are categorised into different genres which cater to various listener moods. Users prefer to listen to music that best suits their mood. Thus considering the need for such classification, research works are being carried out to develop methodologies that can distinguish the music based on individual mood. In this research, instead of using the traditional method of audio feature analysis, we propose to develop a system which analyses the lyrics dataset of the songs based on the features extracted from the training phase and we can predict the mood of the song that is presented to the system at the validation stage. The proposed system is considering five moods containing one hundred songs each, for the validation purpose. The system is capable of predicting the mood of the song based on the analysis of the lyric text.