Naive Bayes classifiers for music emotion classification based on lyrics

There is a constantly growing interest in evaluating music information retrieval (MIR) systems that can provide effective management of the music resources. The crucial characteristic of music is its emotion, which reflect the human's perception. To do the automatic classification of Chinese music emotions more effective, we use the lyrics of music to analysis and classify music based on emotion. There are many algorithms to achieve text classification, and one of the most popular algorithms is Naive Bayes algorithm. Although it is simple, it can classify text effectively. In this paper, we crawl the music lyrics and their labels from a popular website named Baidu music and make our four different datasets. We also train four classifiers with different datasets and report their performance. We evaluate the classifiers trained by four different datasets, and the final accuracy we get is approximately 68%.

[1]  J. Russell A circumplex model of affect. , 1980 .

[2]  Tian Yu,et al.  Chinese Web Text Classification System Model Based on Naive Bayes , 2010, 2010 International Conference on E-Product E-Service and E-Entertainment.

[3]  J. J. Rocchio,et al.  Relevance feedback in information retrieval , 1971 .

[4]  Gerard Salton,et al.  A vector space model for automatic indexing , 1975, CACM.