基于层次结构的多策略中文微博情感分析和特征抽取

摘要
参考文献
相关文章 (15)

全文: PDF (2249 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要随着Web2.0时代的兴起,与微博相关的研究得到了学术界和工业界的广泛关注。该文使用新浪API获取数据,针对中文微博消息展开了情感分析方面的研究。我们对于三种情感分析的方法进行了深入研究,包括表情符号的规则方法、情感词典的规则方法、基于SVM的层次结构的多策略方法,实验表明基于SVM的层次结构多策略方法效果最好。其次,针对层次结构的多策略方法的特征选择进行了详细分析,包括主题无关、主题相关的特征。实验表明使用主题无关的特征时获得的准确率为66.467%。引入主题相关的特征后,准确率提升至67.283%。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	谢丽星1
	周明2
	孙茂松1

关键词 ：新浪微博, 情感分析, SVM

Abstract：With the development of Web 2.0, micro blog has drawn substantial attention from both academia and industry communities. This paper utilizes micro blog API from Sina and carries out sentiment analysis on Chinese micro blog. We compare performances of three method, based on the emoticon, the sentiment lexicon and the hybrid approach over hierarchical structure using SVM, respectively. Through the experiments, we find that SVM based hybrid approach achieves the best performance. Furthermore, we analyze the contribution of various features in this model, including target-independent features and target-dependent features. Experimental results show that SVM based method can gain an accuracy of 66.467% with target-independent features, and an improved accuracy of 67.283% with the addition of target-dependent features.
Key wordssina micro blog; sentiment analysis; SVM

Key words： sina micro blog sentiment analysis SVM

收稿日期: 2011-06-10

中图分类号:

TP391

基金资助:国家自然科学基金资助项目(60873174)

作者简介: 谢丽星(1987—),女,硕士,主要研究方向为缩略语识别、输入法和中文微博的情感分析;孙茂松(1962—),男,博士,清华大学计算机系教授,博士生导师,主要研究方向为自然语言处理、信息检索和社会计算;周明(1964—),男,博士,微软亚洲研究院主任研究员,博士生导师,主要研究方向为自然语言处理、机器翻译、搜索引擎和社会关系网络。

链接本文:

http://jcip.cipsc.org.cn/CN/Y2012/V26/I1/73

[1] M.Q. Hu, B. Liu. Mining and Summarizing Customer Reviews[C]//ACM SIGKDD 2004: 168-177.
[2] Bo Pang, Lillian Lee. Opinion mining and sentiment analysis[C]//Foundations and Trends in Information Retrieval, 2(1-2): 1-135.
[3] M.Q. Hu, B. Liu. Opinion Extraction and Summarization on the Web[C]//AAAI06, Boston: 1621-1624.
[4] H. Yu, V. Hatzivassiloglou. Towards Answering Opinion Question: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences[C]//EMNLP03: 129-136.
[5] Bo Pang, Lillian Lee, Shivakumar Vaithyanathan. Thumbs up? sentiment classification using machine learning techniques[C]//ACL02: 79-86.
[6] Bo Pang, Lillian Lee. A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts[C]//ACL04: 271-278.
[7] E. Riloff, J. Wiebe. 2003. Learning extraction patterns for subjective expressions[C]//EMNLP03: 105-112.
[8] Glance, N., M. Hurst, K. Nigam, et al. 2005. Deriving marketing intelligence from online discussion[C]//SIGKDD05: 419-428.
[9] Wilson, T., J. Wiebe, P. Hoffmann. 2005. Recognizing contextual polarity in phrase-level sentiment analysis[C]//HLT-EMNLP05: 347-354.
[10] Luciano Barbosa, Junlan Feng. 2010. Robust Sentiment Detection on Twitter from Biased and Noisy Data[C]//Coling 2010 (poster paper): 36-44.
[11] Long Jiang, Mo Yu, Ming Zhou, et al. Target-dependent Twitter Sentiment Classification[C]//ACL 2011.
[12] Lun-Wei Ku, Tung-Ho Wu, Li-Ying Lee, et al. 2005. Construction of an Evaluation Corpus for Opinion Extraction[C]//In NTCIR-5 Japan, 2005: 513-520.
[13] S. Dasgupta, V. Ng. Mine the Easy, Classify the Hard: A Semi-Supervised Approach to Automatic Sentiment Classification[C]//ACL09: 701-709.
[14] Fangtao Li, Nathan Liu, Hongwei Jin, et al. Incorporating Reviewer and Product Information for Review Rating Prediction[C]//IJCAI 2011.
[15] V. Hatzivassiloglou, J. Wiebe. Effects of adjective orientation and gradability on sentence subjectivity[C]//COLING00: 299-305.
[16] P. Turney. 2002. Thumbs up or thumbs down Semantic Orientate-on Applied to Unsupervised Classification of reviews[C]//ACL02: 417-424.
[17] Tetsuya Nasukawa, Jeonghee Yi. 2003. Sentiment Analysis: Capturing Favorability Using Natural Language Processing[C]//Proceedings of the 2nd International Conference on Knowledge Capture: 70-77.
[18] Xiaowen Ding, Bing Liu. 2007. The Utility of Linguistic Rules in Opinion Mining[C]//SIGIR-2007 (poster paper), 811-812.
[19] Minqing Hu, Bing Liu. Mining and summarizing customer reviews[C]//KDD-2004 (full paper), Seattle, Washington, USA, Aug 22-25, pp.168-177.
[20] Dmitry Davidiv, Oren Tsur, Ari Rappoport. Enhanced Sentiment Learning Using Twitter Hash-tags and Smileys[C]//Coling 2010 (poster paper), pp.241-249.
[21] Alec Go, Richa Bhayani, Lei Huang. 2009. Twitter Sentiment Classification using Distant Supervision[R]. Technical report, Stanford Digital Library Technologies Project.
[22] Ravi Parikh, Matin Movassate. 2009. Sentiment Analysis of User-Generated Twitter Updates using Various Classification Techniques[R]. CS224N Final Report: 1-18.
[23] Zhao Jun, Liu Kang, Wang Gen. Adding Redundant Features for CRFs-based Sentence Sentiment Classification[C]//EMNLP 2008: 117-126.
[24] Lanjun Zhou, Yunqing Xia, Binyang Li et al. WIA-Opinmine System in NTCIR-8 MOAT Evaluation[C]//NTCIR-8 Workshop Meeting, 2010.
[25] 李寿山,黄居仁. 基于Stacking组合分类方法的中文情感分类研究[J]. 中文信息学报,2010,24(5): 56-61.