基于双语词典的微博多类情感分析方法

doi:10.3969/j.issn.0372-2112.2016.09.007

电子学报 ›› 2016, Vol. 44 ›› Issue (9): 2068-2073.DOI: 10.3969/j.issn.0372-2112.2016.09.007

基于双语词典的微博多类情感分析方法

栗雨晴^1,2, 礼欣^1,2, 韩煦¹, 宋丹丹^1,2, 廖乐健^1,2

1. 北京理工大学计算机学院, 北京 100081;
2. 北京市海量语言信息处理与云计算应用工程技术研究中心, 北京 100081

收稿日期:2015-02-03 修回日期:2015-07-20 出版日期:2016-09-25
- 通讯作者:
- 礼欣
- 作者简介:
- 栗雨晴 女,1991年7月出生于北京市.现为北京理工大学硕士研究生.主要研究方向为社交网络、文本情感分析.E-mail:liyqyimy@163.com
- 基金资助:
- 国家重点基础研究发展规划 (973计划）项目 (No.2013CB329605）; 国家自然科学基金 (No.61300178）

A Bilingual Lexicon-Based Multi-class Semantic Orientation Analysis for Microblogs

LI Yu-qing^1,2, LI Xin^1,2, HAN Xu¹, SONG Dan-dan^1,2, LIAO Le-jian^1,2

1. School of Computer Science, Beijing Institute of Technology, Beijing 100081, China;
2. Beijing Engineering Application Research Center of High Volume Language Information Processing and Cloud Computing, Beijing 100081, China

Received:2015-02-03 Revised:2015-07-20 Online:2016-09-25 Published:2016-09-25
- Supported by:
- Program of National Program on Key Basic Research Project (973 Program) (No.2013CB329605); National Natural Science Foundation of China (No.61300178)

摘要/Abstract

摘要：

现有微博文本情感分析方法多面向单一语种语料，如：中文语料.但是，中英文搭配使用的表达习惯已逐渐成为个体意见表达的重要形式.本文提出一种基于双语词典的多类情感分析方法，通过构建双语多类情感词典对微博文本进行多分类语义倾向性分析，以便更准确有效捕捉群体意见，及时发现社会舆论倾向.通过与多数投票算法、支持向量机算法、基于余弦距离的K近邻分类算法相比，本文提出的基于双语词典的多类情感分析模型具有良好的分类效果，其在分类准确率、F1值等方面都有明显提高.

关键词: 双语语义倾向性分析, 半监督高斯混合模型, 相对熵, 情感词典

Abstract:

Most of the existing Weibo sentiment analysis focuses on monolingual corpus like Chinese.However,a mixed use of Chinese and English becomes a popular form of expression.To better capture the social attention on public events,this paper proposes a bilingual lexicon based multi-class semantic orientation analysis for bilingual microblogs.We compare our proposed methodologies with majority vote,support vector machine (SVM) and K-nearest neighbor (KNN) by using cosine similarity which are competitive baseline methods.The experimental results show that our proposed methods outperform the three approaches we mentioned in terms of the accuracy and F1 score.

Key words: bilingual semantic orientation analysis, semi-supervised gaussian mixture model(Semi-GMM), Kullback-Leibler divergence, sentiment lexicon

中图分类号:

TP391
H085.5

栗雨晴, 礼欣, 韩煦, 等. 基于双语词典的微博多类情感分析方法[J]. 电子学报, 2016, 44(9): 2068-2073.

LI Yu-qing, LI Xin, HAN Xu, et al. A Bilingual Lexicon-Based Multi-class Semantic Orientation Analysis for Microblogs[J]. Acta Electronica Sinica, 2016, 44(9): 2068-2073.

参考文献

[1] Melville P,Gryc W,Lawrence R D.Sentiment analysis of blogs by combining lexical knowledge with text classification[A].Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining[C].New York:ACM SIGKDD Explorations Newsletter,2009.1275-1284.
[2] Wan X.Bilingual co-training for sentiment classification of Chinese product reviews[J].Computational Linguistics,2011,37(3):587-616.
[3] Meng X,Wei F,Liu X,et al.Cross-lingual mixture model for sentiment classification[A].Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics:Long Papers-Volume 1[C].Stroudsburg:Association for Computational Linguistics,2012.572-581.
[4] Pang B,Lee L.Opinion mining and sentiment analysis[J].Foundations and Trends in Information Retrieval,2008,2(1-2):1-135.
[5] Li Y,Li X,Li F,et al.A lexicon-based multi-class semantic orientation analysis for microblogs[A].Web Technologies and Applications[C].Cham:Springer International Publishing,2014.81-92.
[6] Dong Z,Dong Q.HowNet and the Computation of Meaning[M].Singapore:World Scientific,2006.
[7] Miller G A.WordNet:a lexical database for English[J].Communications of the ACM,1995,38(11):39-41.
[8] Hu M,Liu B.Opinion extraction and summarization on the web[A].Proceedings of the 21st National Conference on Artificial Intelligence(AAAI 2006)[C].California:AAAI Press,2006.1621-1624.
[9] Zhu Y L,Min J,Zhou Y,et al.Semantic orientation computing based on HowNet[J].Journal of Chinese Information Processing,2006,20(1):14-20.
[10] Chen J,Xue N,Palmer M S.Using a smoothing maximum entropy model for Chinese nominal entity tagging[A].Natural Language Processing-IJCNLP 2004[C].Heidelberg:Springer-Verlag Berlin Heidelberg,2004.493-499.
[11] Seghouane A K,Amari S I.The AIC criterion and symmetrizing the Kullback-Leibler divergence[J].IEEE Transactions on Neural Networks,2007,18(1):97-106. of Chinese Information Processing, vol. 20, no. 1, pp. 14{20, 2006.
[14]P. S. Dodds, K. D. Harris, I. M. Kloumann, C. A. Bliss, and C. M. Danforth,”Temporal patterns of happiness and information in a global social network: Hedonometrics and twitter," PloS one, vol. 6, no. 12, p. e26752, 2011.
[15]W. Parrott, Emotions in social psychology: Essential readings. Psychology Press, 2001.
[16]http://ictclas.nlpir.org/.
[17]Q. Ye, Z. Zhang, and R. Law, “Sentiment classi_cation of online reviews to travel destinations by supervised machine learning approaches," Expert Systems with Applications, vol. 36, no. 3, pp. 6527{6535, 2009.
[18]L. Ronglu, W. Jianhui, C. Xiaoyun, T. Xiaopeng, and H. Yunfa, “Using maximum entropy model for chinese text categorization [j]," Journal of Computer Research and Development, vol. 1, pp. 22{29, 2005.
[19]D. H. Johnson, S. Sinanovic, et al., “Symmetrizing the kullback-leibler distance," tech. rep., Technical report, Rice University, 2001.
[20]L.-V. Nguyen-Dinh, M. Rossi, U. Blanke, and G. Troster, “Combining crowdgenerated media and personal data: semi-supervised learning for context recognition," in Proceedings of the 1st ACM international workshop on Personal data meets distributed multimedia, pp. 35{38, ACM, 2013

基于双语词典的微博多类情感分析方法

A Bilingual Lexicon-Based Multi-class Semantic Orientation Analysis for Microblogs

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics