一种新闻评论情感词典的构建方法  

Construction Method of Sentiment Lexicon for News Reviews

作　　者：周咏梅[1] 阳爱民[1] 杨佳能[2] 

机构地区：[1]广东外语外贸大学思科信息学院,广州510006 [2]广东外语外贸大学国际工商管理学院,广州510006

出　　处：《计算机科学》2014年第8期67-69,80,共4页Computer Science

基　　金：国家社科基金项目(12BYY045);教育部人文社会科学研究青年项目(10YJCZH247);广东省科技计划项目(2010B031000014);教育部新世纪优秀人才支持计划(NCET-12-0939)资助

摘　　要：情感词典研究是文本情感分析领域的一个重要内容;基于情感词典的文本情感分析方法是一种非常有效的方法。互联网上的新闻评论包含评论人的情感,对其情感进行自动分析研究是非常有意义的。借鉴图排序模型的原理,提出一种新闻评论情感词典构建方法,该方法首先通过新闻评论语料和基础情感词典获得评论情感词集和种子词,然后根据提出的基于PageRank算法的方法判定评论情感词集的极性并计算其强度,进而构建新闻评论情感词典。实验从情感词判定的准确性和基于构建的情感词典的分类性能两个方面验证了所提方法的有效性。Research on sentiment lexicon is an important content on text sentiment analysis research field. The method of text sentiment analysis based on sentiment lexicon is very effective. It is very meaningful on automatic analysis senti- ment for news reviews on internet. In this paper,a construction method of sentiment lexicon for news reviews was pro- posed, which learns Graph-Ranking model principle. The basic idea of the proposed method is as follows. Firstly, Get the word set of news reviews and the seed words with the corpus and basic sentiment lexicon. Then calculate the strength and polarity of the word set of news reviews according to the proposed algorithm based on PageRank. Finally, Construct the sentiment lexicon for news reviews. From two aspect the experiments show that the proposed method is effective, one is the accuracy of deciding the polarity of sentiment words, the other is the classification performance using the sen- timent lexicon which was constructed by proposed method.

关 键 词：情感词典 图排序 PAGERANK算法 新闻评论 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]