基于图模型和多分类器的微博情感倾向性分析  

Emotional Orientation Analysis of Microblog Based on Graph Model and Multiple Classifiers

作　　者：黄挺[1] 姬东鸿[1] 

机构地区：[1]武汉大学计算机学院,武汉430072

出　　处：《计算机工程》2015年第4期171-175,共5页Computer Engineering

基　　金：国家自然科学基金资助重点项目(61133012);国家自然科学基金资助面上项目(61173062)

摘　　要：为研究情感词对情感倾向分析的作用,提高微博情感分析性能,提出一种情感词图模型的方法,利用PageRank算法计算出情感词的褒贬权值,将其作为条件随机场模型的特征,预测具体语言环境下的情感词倾向。结合具体语境下的情感词倾向,利用支持向量机模型进行微博语料的主客观分类和情感倾向分类。实验结果表明,图模型构造的情感词典增加了具体语境下情感词倾向预测的准确性,具体语境下的情感词倾向预测对主客观分类和情感倾向分类有明显的改善。For the further research of the function of emotional words on emotional analysis and the improvement of microblog emotional analysis method,this paper proposes a research approach to construct emotional w ords graph model using relations betw een emotional w ords. The emotional value of appraisal calculated by PageRank algorithm and trained as the feature of conditional random field model so as to forecast the tendency of emotional w ords in specific situations,through w hich subjectivity classification and emotional tendency analysis of microblog can be made w hen integrated w ith Support Vector M achine（ SVM） model. Experimental results show that emotional lexicon constructed by graph model enhances accuracy of the prediction of emotional w ord in specific situations w hich is also helpful for subjectivity classification and emotional tendency analysis of mircroblog.

关 键 词：图模型 情感词 条件随机场 支持向量机 网页排序算法 倾向性分析 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]