节点文献
基于语境歧义词的句子情感倾向性分析
Sentiment Analysis of Sentence Based on Ambiguous Words
【Author】 Song Yanxue,Zhang Shaowu,Lin Hongfei School of Computer Science and Technology,Dalian University of Technology,Dalian 116024
【机构】 大连理工大学计算机科学与技术学院;
【摘要】 目前,在自然语言处理领域,关于词语搭配方面的研究主要是在语料基础上抽取搭配,本文从情感的角度研究语境歧义词的搭配,这种搭配对文本情感倾向性分析方面具有实际重要的意义。首先使用关联规则挖掘的方法确定语境歧义词候选搭配集,然后通过PMI过滤后判断每对搭配词是否具有情感倾向性,最终构建语境歧义词搭配词典。我们采用语义分析的方法,在构建的语境歧义词搭配词典基础上对句子进行情感倾向性分析。通过在COAE2008语料集和情感语料库上进行实验,证明了在判断句子情感倾向性时考虑到语境歧义词的重要性,其对句子进行情感倾向性判断的正确率有很大的影响。
【Abstract】 Currently,in natural language processing,the research on the collocation words is mainly about abstracting collocations from corpus.In this paper,we will study the ambiguous collocations from the aspect of analyzing sentiment,this collocations are important for text analyzing sentiment First,we will use Association Rule to determine if word pairs are collocations,and cut off some ones that are not necessary though PMI,then determine whether the collocations have ambiguity, after that,we will built a ambiguous collocations dictionary on which we determine sentences’ tendency by the method of Semantic Analysis.Experiments we worked on the COAE2008 corpus showed that ambiguous collocations is very important and essential on the sentiment analysis,it can make a large influence on the accuracy of sentiment analysis.
【Key words】 ambiguous collocations; association rule; orientation; affective computing;
- 【会议录名称】 中国计算语言学研究前沿进展(2009-2011)
- 【会议名称】第十一届全国计算语言学学术会议
- 【会议时间】2011-08-20
- 【会议地点】中国河南洛阳
- 【分类号】TP391.1;TP311.13
- 【主办单位】中国中文信息学会