汉语主观性词典创建方法  

Creation method of Chinese subjective lexicon

作　　者：张靖[1] 金浩[2] 

机构地区：[1]攀枝花学院网络中心,四川攀枝花617000 [2]南京大学计算机科学与技术系,江苏南京210093

出　　处：《通信学报》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)~~

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.

关 键 词：情感分析 主观性词典 创建方法 机器学习 模型 算法 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]