计算机科学 ›› 2014, Vol. 41 ›› Issue (8): 67-69.doi: 10.11896/j.issn.1002-137X.2014.08.014

• 2013年全国理论计算机科学学术年会 • 上一篇    下一篇

一种新闻评论情感词典的构建方法

周咏梅,阳爱民,杨佳能   

  1. 广东外语外贸大学思科信息学院 广州510006;广东外语外贸大学思科信息学院 广州510006;广东外语外贸大学国际工商管理学院 广州510006
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家社科基金项目(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

Construction Method of Sentiment Lexicon for News Reviews

ZHOU Yong-mei,YANG Ai-min and YANG Jia-neng   

  • Online:2018-11-14 Published:2018-11-14

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。

关键词: 情感词典,图排序,PageRank算法,新闻评论

Abstract: 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 sentiment for news reviews on internet.In this paper,a construction method of sentiment lexicon for news reviews was proposed,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 sentiment lexicon which was constructed by proposed method.

Key words: Sentiment lexicon,Graph-ranking,PageRank algorithm,News reviews

[1] 杜伟夫.文本倾向性分析中的情感词典构建技术研究[D].哈尔滨:哈尔滨工业大学,2010
[2] 许静芳,李星,李粤.信息检索中主题式词典的构建方法[J].计算机工程,2005(21):153-155
[3] 柳位平,朱艳辉,栗春亮,等.中文基础情感词词典构建方法研究[J].计算机应用,2009(10):2875-2877
[4] Xu G E,Meng Xin-fan,Wang Hou-feng.BuildChinese emotion-lexicons using a graph-based algorithm and multiple resources [C]∥Proceedings of the 23rd International Conference on ComputationalLinguistics.Stroudsburg,PA:Association for Computational Linguistics,2010:1209-1217
[5] Kim S M,Hovy E.Identifying and analyzing judgment opinions [C]∥Proceedings of the Main Conference on Human LanguageTechnology Conference of the North American Chapter of the AssociationofComputational Linguistics.Stroudsburg,PA:Association for Computational Linguistics,2006:200-207
[6] Kim S M,Hovy E.Automatic detection of opinion bearing wordsand sentences[C]∥Proceedings of the Second International JointConference on Natural Language Processing.JejuIsland:[s.n],2005:61-66
[7] Hatzivassiloglou V,Mckeown K.Predicting the semanticorientation of adjectives [C]∥ACL-97:Proceedings of the 35thAnnual Meeting of the Association for Computational Linguistics.Madrid,Spain:[s.n],1997:174-181
[8] Velikovich L,Blair-Goldensohn S,Hannan K,et al.The viability of Web-derived polarity lexicons[C]∥Proceedings ofthe North American Chapter of the Association for Computational Linguistics.Stroudsburg,PA:Association for Computational Linguistics,2010:777-785
[9] Turney P,Littman M L.Measuring praise and criticism:Inferen-ceof semantic orientation from association[J].ACM Transactionson Information Systems,2003,1(4):315-346
[10] Brin S,Page L,Motwami R,et al.The PageRank Citation Ranting:Bringing Order to the Web[R]. Stanford:Stanford University,1999
[11] 徐琳宏,林鸿飞,潘宇,等.情感词汇本体的构造[J].情报学报,2008,27(2):180-185
[12] 杨鼎,阳爱民.一种基于情感词典和朴素贝叶斯的中文文本情感分类方法[J].计算机应用研究,2010,27(10):3737-3739

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!