This paper proposes a music genre classification method based on web mining. It uses the user tags of the Last.fm2 music website as features to compare the similarity of music artists and classify genres based on the similarity between artists. The similarity between artists is obtained by calculating the co-occurrence of tags, and the music genre classification uses the k-nearest neighbor (k-NN) method. Experiments show that using music tags to classify music artists can achieve a high accuracy rate. The method proposed in this paper is better than the music genre classification method based on web mining proposed in the literature [1], and the classification accuracy rate is increased from 89.5% to 95%.
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore