LDA Based Emotion Recognition from Lyrics
Music is one way to express emotion. Music can be felt/heard either using an instrument or as a song which is a combination of instrument and lyrics. Emotion Recognition in a song can be done either using musical features or lyrical features. But at times musical features may be misinterpreting, when the music dominates the lyrics. So a system is proposed to recognize emotion of the song using Latent Dirichlet Allocation (LDA) modelling technique. LDA is a probabilistic, statistical approach to document modelling that discovers latent semantic topics in large corpus. Since there is a chance of more than one emotion occurring in a song, LDA is used to determine the probability of each emotion in a given song. The sequences of N-gram words along with their probabilities are used as features to construct the LDA. The system is evaluated by conducting a manual survey and found to be 72% accurate.
KeywordsSupport Vector Regression Emotion Recognition Latent Dirichlet Allocation Latent Dirichlet Allocation Model Music Information Retrieval
Unable to display preview. Download preview PDF.
- 3.Xiao, H., Bay, M., Downie, J.S.: Creating a simplified music mood classification groundtruth set. In: Proceedings of the 8th International Conference on Music Information Retrieval, pp. 309–310 (2007)Google Scholar
- 4.Yang, D., Lee, W.: Disambiguating music emotion using software agents. In: Proceedings of the 5th International Conference on Music Information Retrieval, pp. 218–223 (2004)Google Scholar
- 5.Trung-Thanh, D., Shirai, K.: Machine learning approaches for mood classification of songs toward music search engine. In: International Conference on Knowledge and Systems Engineering, pp. 144–149 (2009)Google Scholar
- 6.Chen, R.H., Xu, Z.L., Zhang, Z.X., Luo, F.Z.: Content based music emotion analysis and recognition. In: Proceedings of 2006 International Workshop on Computer Music and Audio Technology, pp. 68–75 (2006)Google Scholar
- 7.Byeong-Jun, H., Ho, S., Dannenberg, R.B., Hwang, E.: SMERS: Music emotion recognition using support vector regression. In: Proceedings of the 10th International Society for Music Information Conference, pp. 651–656 (2009)Google Scholar
- 8.Yang, D., Lee, W.-S.: Music emotion identification from lyrics. In: 11th IEEE International Symposium In Multimedia, pp. 624–629 (2009)Google Scholar
- 10.Qingqiang, W., Zhang, C., Deng, X., Jiang, C.: LDA-based model for topic evolution mining on text. In: 6th International Conference in Computer Science & Education, pp. 946–949 (2011)Google Scholar
- 11.Wu, M., Dong, Z.C., Weiyao, L., Qiang, W.Q.: Text topic mining based on LDA and co-occurrence theory. In: 7th International Conference on Computer Science & Education, pp. 525–528 (2012)Google Scholar
- 12.Sridhar, R., Geetha, T.V., Subramanian, M., Lavanya, B.M., Malinidevi, B.: Latent Dirichlet Allocation Model for raga identification of carnatic music. Journal of Computer Science, 1711–1716 (2011)Google Scholar
- 14.Hu, D., Saul, L.: Latent Dirichlet Allocation for text, images, and music. University of California (2009)Google Scholar