音频信号在歌曲情感分析中难以奏效,所以该文提出以歌词作为歌曲情感分析的依据,采取基于情感单元的情感向量空间模型(s-VSM)进行歌词情感分析。该模型较好地解决了基于词汇的向量空间模型(w-VSM)在文本表示效率、歧义、情感功能和数据稀疏性等方面的不足。同时,该文将情感词词频与Thayer二维情感压力模型相结合,提出了“轻松”、“压抑”之外的“复杂”、“含蓄”两类新的情感压力类别。实验证明 (1)s-VSM模型在歌词情感分类中优于传统方法;(2)四类情感压力模型对歌词情感分析很有帮助。
Abstract
Song sentiment analysis has not been satisfactorily addressed in audio signal processing community. In this paper,the lyric is used as proof for song sentiment analysis and the sentiment vector space model (s-VSM) is proposed to represent given lyric. Compared to the word-based vector space model (w-VSM), the s-VSM model successfully addresses the critical issues on text representation efficiency, ambiguity, functionality and data sparseness. Furthermore, the two-dimension Thayer sentiment stress model, i.e. light-hearted and heavy-hearted, are extended to a four-dimension model to incorporate two extra sentiment stress levelscomplicated and implied level. Experiments show that 1) the s-VSM model outperforms the traditional methods; and 2) the four-dimension sentiment stress model is helpful to further improve performance of song sentiment analysis.
Key wordscomputer application; Chinese information processing; sentiment analysis; sentiment vector space model; sentiment stress
关键词
计算机应用 /
中文信息处理 /
文本情感分析 /
情感向量空间模型 /
情绪压力
{{custom_keyword}} /
Key words
computer application /
Chinese information processing /
sentiment analysis /
sentiment vector space model /
sentiment stress
/
/
/
/
/
/
/
/
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] R. E. Thayer. The Biopsychology of Mood and Arousal[M].New York, Oxford University Press. 1989.
[2] T. Li and M. Ogihara. Content-based music similarity search and emotion detection[C]//Proc. IEEE Int. Conf. Acoustic, Speech, and Signal Processing, 2006: 17-21.
[3] L. Lu, D. Liu and H. Zhang. Automatic mood detection and tracking of music audio signals[J].IEEE Transactions on Audio, Speech & Language Processing, 2006, 14(1): 5-18.
[4] R.H. Chen, Z. L. Xu, Z. X. Zhang and F. Z. Luo. Content Based Music Emotion Analysis and Recognition[C]//Proc. of 2006 International Workshop on Computer Music and Audio Technology, 2006: 68-75.
[5] Y. Xia, L. Wang, K.-F. Wong and M. Xu. Sentiment Vector Space Model for Lyric-based Song Sentiment Classification[C]//Proc. of ACL-08: HLT, Short Papers (Companion Volume): 133-136, Columbus, Ohio, USA, June, 2008.
[6] T. Joachims. Learning to Classify Text Using Support Vector Machines Methods, Theory, and Algorithms[M]: Kluwer, 2002.
[7] Z. Dong and Q. Dong. HowNet and the Computation of Meaning[M]. World Scientific Publishing, 2006.
[8] J. Ma, Y. Zhang, T. Liu, S. Li. A Statistical Dependency Parser of Chinese under Small Training Data[C]//Proc. of IJCNLP-2004, 1999: 1-5.
[9] Y. Yang and X. Liu. A Re-Examination of Text Categorization Methods[C]// Proc. of SIGIR'99, 1999: 42-49.
[10] Y. Yang and J. O. Pedersen. A comparative study on feature selection in text categorization[C]//Proc. of ICML'97, 1997: 412-420.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
自然科学基金资助项目(60703051);国际科技合作项目(2009DFA12970)
{{custom_fund}}
PDF(707 KB)
