Music Emotion Classification: Dataset Acquisition and Comparative Analysis



In this paper we present an approach to emotion classification in audio music. The process is conducted with a dataset of 903 clips and mood labels, collected from Allmusic1 database, organized in five clusters similar to the dataset used in the MIREX2 Mood Classification Task. Three different audio frameworks – Mar-syas, MIR Toolbox and Psysound, were used to extract several features. These audio features and annotations are used with su-pervised learning techniques to train and test various classifiers based on support vector machines. To access the importance of each feature several different combinations of features, obtained with feature selection algorithms or manually selected were tested. The performance of the solution was measured with 20 repetitions of 10-fold cross validation, achieving a F-measure of 47.2% with precision of 46.8% and recall of 47.6%.


music emotion recognition, music information retrieval

Related Project

MOODetector: A System for Mood-based Classification and Retrieval of Audio Music


15th International Conference on Digital Audio Effects – DAFx’12, September 2012

PDF File

Cited by

Year 2015 : 1 citations

 Dufour, I. (2015). Improving Music Mood Annotation Using Polygonal Circular Regression. MSc Thesis. Department of Computer Science, University of Victoria, Victoria, BC, Canada.

Year 2014 : 4 citations

 Baume, Chris, et al. "Selection of audio features for music emotion recognition using production music." Audio Engineering Society Conference: 53rd International Conference: Semantic Audio. Audio Engineering Society, 2014.

 Xu, Jieping, et al. "Source separation improves music emotion recognition." Proceedings of International Conference on Multimedia Retrieval. ACM, 2014.

 Lee, Jin Ha, and Xiao Hu. "Cross-cultural similarities and differences in music mood perception." iConference 2014 Proceedings (2014).

 2. da Costa, DMR. (2014, November). Effects of music preference and selection on stress management. MSc Thesis. University of Minho.

Year 2013 : 2 citations

 1. Baume, C. (2013, May). Evaluation of Acoustic Features for Music Emotion Recognition. In Audio Engineering Society Convention 134. Audio Engineering Society.

 Saari, Pasi, et al. "Using semantic layer projection for enhancing music mood prediction with audio features." Sound and Music Computing Conference, Stockholm, Sweden. 2013.