Abstract: Among all the applications for China Internet users, instant message has first-largest users, search engine has the second-largest users and the web music has the third-largest users. Web music and its application technology have been popular with academics. Music plays an important role as a communication media in human communication which carries abundant information of emotion. As a result, musical emotion analysis has been paid more attention. During the process of musical emotion analysis which is based on lyric texts, a reasonable musical semantic lexicon will provide a more accurate result. This paper is about how to build a Chinese musical emotional lexicon which is based on the improved model of Hevner emotional ring model and the semantic knowledge resources provided by HowNet and a text corpus of lyrics. Also it realizes a method of lyric emotional classification with the help of emotional VSM, emotional lexicon and lyrics speed. The experiments show that the Chinese emotional lexicon built here is more suitable in the area of music than the lexicon built by manual.

Key words: Chinese emotional lexicon, musical emotion analysis, Hevner emotional ring model, HowNet

摘要： 作为仅次于及时通信和搜索引擎的中国互联网网民第三大应用，网络音乐及其应用技术受到业界学者的青睐。音乐作为人类最重要的交流媒介，携带着丰富的情感信息，计算机音乐情感分析更是得到人机情感交互技术领域的高度重视。在基于歌词文本的音乐情感分析过程中，一部合理的音乐领域情感词典，将提供更加细致、更加准确的分析结果。以改进后的Hevner情感环模型为基础，借助HowNet所提供的语义资源和从网络爬取的歌词文本语料库，构建了一部树形层次结构的音乐领域中文情感词典，并利用LRC歌词携带的时间标签获取歌曲的语速信息，实现了基于情感向量空间模型和情感词典的歌词情感分类。实验表明与人工构建的情感词典相比，所构建的情感词典更适用于音乐领域。

关键词: 中文情感词典, 音乐情感分析, Hevner情感环模型, 知网