基于情感向量空间模型的歌词情感分析  

Lyric-Based Song Sentiment Analysis by Sentiment Vector Space Model

作　　者：夏云庆[1] 杨莹[2] 张鹏洲[2] 刘宇飞[3] 

机构地区：[1]清华大学信息技术研究院,北京100084 [2]中国传媒大学计算机学院,北京100024 [3]深圳大学电子科学与技术学院,广东深圳518000

出　　处：《中文信息学报》2010年第1期99-103,共5页Journal of Chinese Information Processing

基　　金：自然科学基金资助项目(60703051);国际科技合作项目(2009DFA12970)

摘　　要：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。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 suc- cessfully 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 levels： complicated 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.

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 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]