摘要
根据汉语情感分析现状和需求,分析和研究了从目标语料库自动获取汉语主观性词典,提出了一种主观性词典创建方法,定义了主观性词典和语言模型,设计了自适应主观性自举算法和主观性属性特征模型,实现了主观性词条中情感倾向、主观性强度和词汇主客观自动判别。采用机器学习方法证明,提出的汉语主观性词典自动创建方法高效,性能优良。
Based on the current situation of and demand for Chinese sentiment analysis,the method of automatically ob-taining subjective lexicon from the target corpus was studied.A creation method of subjective lexicon was presented,the subjective lexicon and language model were defined,a self-adaptive subjectivity bootstrapping algorithm and the charac-teristic model of subjectivity attribute were designed,and all these lead to the realization of the automatic judgment of sentiment polarity,subjectivity intensity and the subjectivity and objectivity of a word in the subjectivity entry.Experi-ments prove that by using machine learning the proposed method of automatic creation of Chinese subjective lexicon is highly efficient and with excellent performance.
出处
《通信学报》
EI
CSCD
北大核心
2010年第S1期172-176,共5页
Journal on Communications
基金
四川省科技基金资助项目(2009zr0159)~~
关键词
情感分析
主观性词典
创建方法
机器学习
模型
算法
sentiment analysis
subjective lexicon
creation method
machine learning
models
algorithms
