基于语义特征的文本情感倾向识别研究  

Text sentiment orientation identification based on semantic feature

作　　者：何坤[1] 李伟生[1] 杨勇[1] 

机构地区：[1]重庆邮电大学计算机科学与技术研究所,重庆400065

出　　处：《计算机应用研究》2010年第3期992-994,共3页Application Research of Computers

基　　金：国家自然科学基金资助项目(60842003)

摘　　要：由于网络评论用语的多样性,常用的文本主题分类方法并不能完全适应情感倾向识别。针对这个问题,从语义理解的角度出发,提出一种基于语义特征的情感倾向识别方法,通过增加语义特征使得原始文本表现出更加明确的情感倾向,并且更加容易区分。实验结果表明了该方法的有效性。Because of the diversity of network comments, common method of text topic classification can not completely adapt to the orientation identification. To solve this problem, this paper proposed a method of text orientation identification based on semantic feature from the point of view of semantic understanding. Expressed sentiment orientation of original text definitely and distinguished original text more precisely than that without semantic feature because of increasing semantic feature. The experimental results indicate the validity of the method.

关 键 词：语义特征 倾向识别 情感分类 主题分类 

分 类 号：TP309.7[自动化与计算机技术—计算机系统结构]