摘要
在线商品评论的情感倾向分析是一个很有研究价值的分类技术。文中采用SVM文本分类算法将在线商品评论进行情感倾向分析,同时,为了克服传统的CHI统计特征选择法的不足,提出了结合方差分析的CHI统计特征选择方法。实验表明:在基于SVM的在线商品评论情感倾向分析中,改进的特征选择方法对在线商品评论的情感分类效果有很好的提升。
Sentiment analysis ol online product reviews is a valuable research classification technique.This paper applies a Chinese text categorization algorithm based on SVM , to analyze the sentimenttendency ol online product reviews, which are positive or negative, at the same time, in order to overcomethe shortcomings ol the traditional C HI feature selection method,the C HI feature selection method basedon analysis ol variance is proposed. The experimental result show the improved feature selection methodhas a good promotion to sentiment analysis ol online product reviews based on SVM .
出处
《信息技术》
2016年第7期172-175,共4页
Information Technology
关键词
商品评论
情感倾向分析
CHI特征选择
支持向量机
product reviews
sentiment analysis
CH I leature selection
support vector machine