基于统计数据的微博表情符分析及其在情绪分析中的应用

J4 ›› 2016, Vol. 38 ›› Issue (03): 577-584.

基于统计数据的微博表情符分析及其在情绪分析中的应用

刘宝芹，牛耘，张景

（南京航空航天大学计算机科学与技术学院,江苏南京 210016）

收稿日期:2015-05-25 修回日期:2015-07-01 出版日期:2016-03-25 发布日期:2016-03-25
基金资助:
国家自然科学基金（61202132）

Statistical analysis of emoticons and
its application in emotion analysis

LIU Baoqin，NIU Yun，ZHANG Jing

（School of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China）

Received:2015-05-25 Revised:2015-07-01 Online:2016-03-25 Published:2016-03-25

摘要/Abstract

摘要：

表情符作为一种新兴的网络语言，受到了越来越多的微博用户的青睐。微博中出现的表情符形象直观地表达了博主的情绪，对情绪分析起着至关重要的作用。首先对大量中文微博中表情符的使用特点、分布情况和情绪表达特点进行了统计分析。然后，人工选取具有代表性且情感倾向明确的表情符作为六类基本情绪的种子表情符。根据目标表情符和六类情绪的种子表情符在微博文本中的共现情况，为其建立六维情绪向量，并将其应用于微博情绪分析。在两个数据集上的实验结果表明，本文建立的表情符情绪向量有效地提高了微博情绪识别的精度。

关键词: 表情符, 情绪向量, 统计分析, 情绪分析

Abstract:

As a new network language, emoticons have earned the favor of an increasing number of Microblog users. Emoticons in microblogs vividly represent blogger’s emotions. We first make a comprehensive analysis of emoticons in a large corpus of Chinese microblogs, including their usage, distribution and characteristics in emotion expression. Secondly, we manually select a list of emoticons that typically indicate six basic emotions as seeds. Based on the cooccurrence between a target emoticon and the seed emoticons in a large corpus, we establish sixdimensioned vectors for the target emoticon and apply them to emotion analysis. Experimental results on two data sets show that the emoticon vectors can effectively improve the precision of microblog emotion recognition.

Key words: emoticon;emotion vectors;statistical analysis;emotion analysis

刘宝芹，牛耘，张景. 基于统计数据的微博表情符分析及其在情绪分析中的应用[J]. J4, 2016, 38(03): 577-584.

LIU Baoqin，NIU Yun，ZHANG Jing. Statistical analysis of emoticons and
its application in emotion analysis [J]. J4, 2016, 38(03): 577-584.

参考文献［19］

［1］	Ekman. Facial expression and emotion ［J］. American Psychologist,1993,48(4):384392.
［2］	Derks D,Bos A E R,Von Grumbkow J.Emoticons in computermediated communication:Social motives and social context［J］.Cyber Psychology & Behavior,2008,11(1):99101.
［3］	Walther J B, D’Addario K P. The impacts on emoticons on message interpretation in computermediated communication［J］.Social Science Computer Review,2001,19(3):324347.
［4］	Tang Shiyao.The communicative imagination of Q era—the structure and function of QQ emoticons［J］.Modern Chinese,2006 (8):8283.(in Chinese)
［5］	Wei Wei. Emotional expression of network emoticons ［J］.Public Communication of Science & Technology,2014(13):2424.(in Chinese)
［6］	Purver M,Battersby S.Experimenting with distant supervision for emotion classification ［C］∥Proc of the 13th Conference of the European Chapter of the Association for Computational Linguistics,2012:482491.
［7］	Zhao J, Dong L, Wu J, et al.Moodlens:An emoticonbased sentiment analysis system for Chinese tweets［C］∥Proc of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2012:15281531.
［8］	Tang D,Qin B,Liu T,et al.Learning sentence representation for emotion classification on microblogs［M］∥Natural Language Processing and Chinese Computing.Berlin:Springer Berlin Heidelberg,2013:212223.
［9］	Davidov D,Tsur O,Rappoport A.Enhanced sentiment learning using twitter hashtags and smileys［C］∥Proc of the 23rd International Conference on Computational Linguistics:Posters,2010:241249.
［10］	Liu Kunlin,Li Wujun,Guo Mingyi,et al.Emoticon smoothed language models for Twitter sentiment analysis［C］∥TwentySixth AAAI Conference on Artificial Intelligence,2012:1.
［11］	Paltoglou G,Thelwall M.Twitter,MySpace,Digg:Unsupervised sentiment analysis in social media［J］.ACM Transactions on Intelligent Systems and Technology (TIST),2012,3(4):6783.
［12］	Jiang Fei, Cui Anqi, Liu Yiqun, et al.Every term has sentiment:Learning from emoticon evidences for Chinese microblog sentiment analysis［C］∥Proc of NLPLL’13,2013:224235.
［13］	Zhang Jing,Zhu Bo,Liang Linlin,et al.Recognition and classification of emotions in the Chinese microblog based on emotional factor ［J］.Acta Scientiarum Naturalium Universitatis Pekinensis,2014,50(1)：7984.(in Chinese)
［14］	Xie Lixing,Zhou Ming,Sun Maosong.Hierarchical structure based hybrid approach to sentiment analysis of Chinese micro blog and its feature extraction ［J］.Journal of Chinese Information Processing,2012,26(1):7383.(in Chinese)
［15］	Pan Minghui,Niu Yun.Emotion recognition of microblogs based on a hybrid lexicon ［J］.Computer Technology and Development,2014,24(9):2832.(in Chinese)
［16］	Chang Chihchung, Lin Chihjen. LIBSVM:A library for support vector machines［J］.ACM Transactions on Intelligent Systems & Technology,2011,2(3):389396.
［17］	NLPIR［EB/OL］.http:∥ictclas.nlpir.org/.
［18］	CLIWC［EB/OL］.http:∥cliwc.blogbus.com.
［19］	Xu Linhong, Lin Hongfei, Pan Yu, et al. Constructing the affective lexicon ontology［J］.Journal of the China Society for Scientific and Technical Information,2008,27(2):180185.(in Chinese)
	附中文参考文献：
［4］	唐师瑶.Q 时代的交际想象——QQ 表情符号的构形规律及功能初探［J］.现代语文,2006 (8):8283.
［5］	魏玮.网络表情符号的情感表达探讨［J］.科技传播,2014(13):2424.
［13］	张晶,朱波,梁琳琳,等.基于情绪因子的中文微博情绪识别与分类［J］.北京大学学报：自然科学版,2014,50(1)：7984.
［14］	谢丽星,周明,孙茂松.基于层次结构的多策略中文微博情感分析和特征抽取［J］.中文信息学报,2012,26(1):7383.
［15］	潘明慧,牛耘.基于多线索混合词典的微博情绪识别［J］.计算机技术与发展,2014,24(9):2832.
［19］	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.