基于中文微博语料的情感倾向性分析

doi:10.6040/j.issn.1671-9352.3.2014.194

山东大学学报（理学版） ›› 2014, Vol. 49 ›› Issue (11): 1-7.doi: 10.6040/j.issn.1671-9352.3.2014.194

• 论文 • 下一篇

基于中文微博语料的情感倾向性分析

罗毅, 李利, 谭松波, 程学旗

中国科学院计算技术研究所, 北京 100190

收稿日期:2014-08-28 修回日期:2014-10-24 出版日期:2014-11-20 发布日期:2014-11-25
作者简介:罗毅(1989- ),男,硕士研究生,主要研究方向为情感分类、自然语言理解.E-mail:luoyi@software.ict.ac.cn
基金资助:
国家自然科学基金资助项目(61232010,61100083);国家重点基础研究发展计划(“九七三”计划)项目(2013CB329601/02);国家高技术研究发展计划(“八六三”计划)项目(2012AA011003);国家科技支撑计划项目(2012BAH39B04);国家安全专项项目(2013A140)

Sentiment analysis on Chinese Micro-blog corpus

LUO Yi, LI Li, TAN Song-bo, CHENG Xue-qi

Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China

Received:2014-08-28 Revised:2014-10-24 Online:2014-11-20 Published:2014-11-25

摘要/Abstract

摘要： 微博的兴起与传播使得短文本情感分类成为目前的热门研究领域.通过对中文微博语料的情感倾向性分析进行研究,提出了一种新的情感分类方法.首先构建了两级情感词典,并对不同级别情感词作不同增强;然后在情感特征方面使用N-Gram方法,尽量获取有限长度博文中的未登录情感词和情感信息.经实验验证与传统方式相比较,该方法的准确率和召回率都有所提高,在COAE2014微博情感倾向性评测任务中也取得了较好的成绩.

关键词: 倾向性分析, 观点挖掘, 情感分类

Abstract: The rise and spread of Micro-blog make sentiment classification on short texts become a hot area. A new method was proposed for Micro-blog sentiment classification. First of all, this method will create an emotional dictionary with two-levels, and the words for different levels will get different enhancement; then in order to get features, N-gram method was used, which found new emotional words and emotional information from a short text. The experiment results show this approach has improved precision and recall rate compared to the traditional ways. This algorithm also did a very good job in COAE 2014.

Key words: tendentious analysis, sentiment classification, opinion mining

中图分类号:

TP391

罗毅, 李利, 谭松波, 程学旗. 基于中文微博语料的情感倾向性分析[J]. 山东大学学报（理学版）, 2014, 49(11): 1-7.

LUO Yi, LI Li, TAN Song-bo, CHENG Xue-qi. Sentiment analysis on Chinese Micro-blog corpus[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(11): 1-7.

参考文献

[1] DAVIDOV D, TSUR O, RAPPOPORT A. Enhanced sentiment learning using Twitter hashtags and smileys[C]//Proceedings of the 23rd International Conference on Computational Linguistics.Beijing: Tsinghua University Press, 2010:241-249.
[2] BARBOSA L, FENG J. Robust sentiment detection on Twitter from biased and noisy data[C]//Proceedings of the 23rd International Conference on Computational Linguistics.Beijing:Tsinghua University Press, 2010:36-44.
[3] HASSAN A, QAZVINIAN V, RADEV D. What's with the attitude? Identifying sentences with attitude in online discussions[C]//Proceedings of 2010 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2010:1245-1255.
[4] MEENA A, PRABHAKAR T, AMATI G, et al. Sentence level sentiment analysis in the presence of conjuncts using linguistic analysis[C]//Advances in Information Retrieval. Heidelberg: Springer Berlin, 2007:573-580.
[5] TURNEY P D. Thumbs up or thumbs down? semantic orientation applied to unsupervised classification of reviews[C]//Proceedings of 40th Annual Meeting of the Association for Computational Linguistics. Somerset: ACL, 2002:417-424.
[6] SOCHER R, PENNINGTON J, HUANG E H, et al. Semi-supervised recursive auto-encoders for predicting sentiment distributions[C]//Proceedings of 2011 Conference on Empirical Methods in Natural Language Processing. [S.l.]:[s.n.], 2011: 151-161.
[7] 王根,赵军. 基于多重标记CRF句子情感分析的研究[C]//内容计算的研究与应用前沿:第九届全国计算语言学学术会议论文集.北京:清华大学出版社, 2007:609-614. WANG Gen, ZHAO Jun. Sentence sentiment analysis based on multi-redundant-labeled CRFs[C]//Advanced Research and Application of Frontier Content Computing: the 9th China National Conference on Computational Linguistics. Beijing: Tsinghua University Press, 2007:609-614.
[8] TAN Chenhao, LEE Lilian, TANG Jie, et al. User-level sentiment analysis incorporating social networks[C]//Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2011:1397-1405.
[9] LI Shoushan, WANG Zhongqing, ZHOU Guodong, et al. Semi-supervised learning for imbalanced sentiment classification[C]//Proceedings of the 22nd International Joint Conference on Artificial Intelligence. [s.l.]: AAAI Press, 2011:1826-1831.
[10] Iadh Ounis, Craig Macdonald, Ian Soboroff. Overview of the TREC 2010 BlogTrack[C]//Proceedings of the 19th Text REtrieval Conference Proceedings (TREC 2010). NIST, 2010.
[11] SEKI Y, KU L-W, SUN L, et al.Overview of multilingual opinion analysis task at NTCIR-8: a step toward cross lingual opinion analysis[C]//Proceedings of the 8th NTCIR Workshop.[S.l.]:[s.n.], 2010:209-220.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于中文微博语料的情感倾向性分析

Sentiment analysis on Chinese Micro-blog corpus

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

多维度评价

本文评价

推荐阅读 0

[1]	杨艳,徐冰,杨沐昀,赵晶晶. 一种基于联合深度学习模型的情感分类方法[J]. 山东大学学报（理学版）, 2017, 52(9): 19-25.
[2]	张克亮,黄金柱,曹蓉,李峰. 基于HNC语境框架和情感词典的文本情感倾向分析[J]. 山东大学学报（理学版）, 2016, 51(7): 51-58.
[3]	刘培玉, 张艳辉, 朱振方, 荀静. 融合表情符号的微博文本倾向性分析[J]. 山东大学学报（理学版）, 2014, 49(11): 8-13.