基于关键词和关键句抽取的用户评论情感分析  

Sentiment Analysis of User Comments Based on Extraction of Key Words and Key Sentences

作　　者：喻影 陈珂[1,2] 寿黎但[1,2] 陈刚[1,2] 吴晓凡[3] YU Ying;CHEN Ke;SHOU Li-dan;CHEN Gang;WU Xiao-fan(College of Computer Science and Technology,Zhejiang University,Hangzhou 310027,China;Key Laboratory of Big Data Intelligent Computing of Zhejiang Province (Zhejiang University),Hangzhou 310027,China;Netease (Hangzhou) Network Co.,Ltd,Hangzhou 310051,China)

机构地区：[1]浙江大学计算机科学与技术学院,杭州310027 [2]浙江省大数据智能计算重点实验室(浙江大学),杭州310027 [3]网易(杭州)网络有限公司,杭州310051

出　　处：《计算机科学》2019年第10期19-26,共8页Computer Science

基　　金：国家重点研发项目(2017YFB1201001);国家自然科学基金项目(61672455);浙江省自然科学基金(LY18F020005)资助

摘　　要：情感分析的一项主要研究任务是根据文档内容对其情感极性(即正类和负类)进行判断。在判断文档的情感极性时,不同的词语和句子具有不同的情感贡献度,因此如何从整个文档中准确地提取与情感分类更相关的词语和句子,从而提升分类性能,成为了一个重要问题。在有监督实验中,基于依存句法关系分析句子的逻辑结构,提取出了与表达情感更相关的词语进行加权,提高了分类性能。在半监督实验中,使用基于中文评论的关键句抽取和分类器融合算法,对整篇文档中包含更多情感词和总结意味的关键句进行了抽取,充分考虑了句子的情感词属性、位置属性、标点符号属性和关键词属性,并且使用分类器融合算法,让置信度最高的子分类器决定分类效果。在大众点评网和头条新闻的数据集上将所提算法与已有的经典算法进行对比,发现所提方法的性能更高,从而证明了基于依存句法分析的关键词抽取和基于特征的中文关键句抽取算法的有效性。One of the main task of sentiment analysis is to determine the polarity of a review whether it is positive or negative according to the content of the document.When determining the emotional polarity of a document,different sentences and words have different emotional contribution on the classification result,so how to extract more related words and sentences becomes an important problem.In the experiment of the supervised classification,this paper used the dependency syntactic analysis to extract the words which are more related to the emotion and can improve the classification effect.In the semi-supervised classification experiment,the key sentence extraction and the combining-classifier method based on the Chinese comments have been used.For key sentence extraction,the proposed approach takes the following attributes into account:sentiment attribute,position attribute,special word attribute and punctuation attri- bute .This approach extracts key sentences containing more emotional words and summary meaning,then uses combining-classifier method to make the sub classifier with the highest confidence to determine the classification effect.The results show that the performance of the proposed method is better than the baseline methods,which proves the validity of keyword extraction based on the dependency parsing and key Chinese sentence extraction algorithms.

关 键 词：情感分析 依存分析 关键句抽取 半监督学习 协同训练 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]