基于情绪特征的中文微博用户性别识别

计算机工程与科学

基于情绪特征的中文微博用户性别识别

刘宝芹，牛耘

（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:2015-07-13 修回日期:2015-09-15 出版日期:2016-09-25 发布日期:2016-09-25
基金资助:
国家自然科学基金（61202132）

Gender recognition of Chinese micro-blog users based on emotion features

LIU Bao-qin，NIU Yun

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

Received:2015-07-13 Revised:2015-09-15 Online:2016-09-25 Published:2016-09-25

摘要/Abstract

摘要：

随着互联网的蓬勃发展，微博受到了越来越多用户的青睐，对微博用户性别的研究也逐渐成为学术界研究的热点。目前，对英文微博文本用户的性别识别已有研究，但针对中文微博用户性别识别的研究较少。从两性表达情绪的差异出发，提出了一种基于情绪特征的中文微博用户性别识别方法。本文考虑的情绪特征包括情绪词特征和与情绪相关的语言风格特征。实验结果表明，利用情绪特征提高了用户性别识别的精度。

关键词: 性别识别, 中文微博, 情绪风格特征, 情绪词特征

Abstract:

With the vigorous development of the Internet, micro-blog service is attracting more and more users.Gender recognition of micro-blog users thereby becomes a hot research topic.Tremendous efforts have been made on gender recognition of Twitter users. However, research on Chinese micro-blogs users is still new. Based on the difference in the emotion expressions between males and females, we propose a gender recognition method of Chinese micro-blog users based on emotion features. The emotion features including emotional words and linguistic style features associated with the emotions. Experimental results show that using emotion features can improve the accuracy of gender recognition.

Key words: gender recognition, Chinese micro-blogs, emotion style features, emotional words

刘宝芹，牛耘. 基于情绪特征的中文微博用户性别识别[J]. 计算机工程与科学.

LIU Bao-qin，NIU Yun. Gender recognition of Chinese micro-blog users based on emotion features [J]. Computer Engineering & Science.

参考文献

［1］Newman M L,Groom C J, Handelman L D, et al. Gender differences in language use: An analysis of 14 000 text samples［J］.Discourse Processes,2008,45(3):211-236.
［2］Thelwall M,Wilkinson D,Uppal S.Data mining emotion in social network communication:Gender differences in MySpace ［J］. Journal of the American Society for Information Science and Technology,2010,61(1): 190-199.
［3］Liu H, Mihalcea R.Of men,women,and computers: Data-driven gender modeling for improved user interfaces［C］∥Proc of the International Conference on Weblogs Social Media, 2007:1.
［4］Mohammad S M,Yang T W.Tracking sentiment in mail: How genders differ on emotional axes［C］∥Proc of the 2nd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis (ACL-HLT 2011),2011: 70-79.
［5］Montero C S, Munezero M, Kakkonen T. Investigating the role of emotion-based features in author gender classification of text［C］∥Proc of the 15th International Conference CICLing 2014,2014: 98-114.
［6］Mukherjee A,Liu B.Improving gender classification of blog authors［C］∥ Empirical Methods in Natural Language Processing, 2010:207-217.
［7］Burger J D,Henderson J,Kim G,et al.Discriminating gender on Twitter［C］∥Proc of the Conference on Empirical Methods in Natural Language Processing,2011:1301-1309.
［8］Ciot M,Sonderegger M,Ruths D.Gender inference of Twitter users in non-English contexts［C］∥Proc of EMNLP, 2013: 1136-1145.
［9］Ai Zamal F,Liu W, Ruths D.Homophily and latent attribute inference: Inferring latent attributes of Twitter users from neighbors［C］∥Proc of ICWSM, 2012:387-390.
［10］Rao D, Yarowsky D, Shreevats A, et al. Classifying latent user attributes in Twitter［C］∥Proc of the 2nd International Workshop on Search and Mining User-generated Contents,2010:37-44.
［11］Sap M,Park G,Eichstaedt J,et al.Developing age and gender predictive lexica over social media［C］∥Proc of EMNLP, 2014: 1146-1151.
［12］Gao Q,Abel F,Houben G J,et al.A Comparative study of users’ microblogging behavior on Sina Weibo and Twitter［C］∥ Proc of User Modeling,Adaptation,and Personalization,2012:88-101.
［13］Wang Jing-jing,Li Shou-shan,Huang Lei.User gender classification in Chinese micro-blog ［J］.Journal of Chinese Information Processing,2014,28(6): 150-155.(in Chinese)
［14］Li L,Sun M,Liu Z.Discriminating gender on Chinese microblog: A study of online behaviour,writing style and preferred vocabulary［C］∥Proc of 2014 10th International Conference on Natural Computation (ICNC),2014: 812-817.
［15］Ekman P. Facial expression and emotion ［J］.American Psychologist,1993,48(4): 384-392.
［16］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)
［17］C-LIWC［EB/OL］.［2015-07-13］.http:∥c-liwc.blogbus.com.
［18］Okearney R, Dadds M. Developmental and gender differences in the language for emotions across the adolescent years［J］.Cognition & Emotion,2010,18(7):913-938.
［19］Tweedie F J,Baayen R H.How variable may a constant be measures of lexical richness in perspective［J］.Computers and the Humanities,1998,32(5): 323-352.
［20］Bamman D,Eisenstein J,Schnoebelen T.Gender in twitter: Styles,stances,and social networks［J］.Cc Gatech Edu,2012,18(2):135.
［21］Plant E A,Hyde J S,Keltner D,et al.The gender stereotyping of emotions［J］.Psychology of Women Quarterly,2000,24(1): 81-92.
［22］Heylighen F,Dewaele J M.Variation in the contextuality of language: An empirical measure［J］.Foundations of Science,2002,7(3):293-340.
［23］NLPIR［EB/OL］.［2015-07-13］.http:∥ictclas.nlpir.org/.
［24］Chang C C,Lin C J.LIBSVM: A library for support vector machines［J］.ACM Transactions on Intelligent Systems & Technology,2011,2(3):389-396.
［25］Li S,Xia R,Zong C,et al.A framework of feature selection methods for text categorization［C］∥Proc of the 47th Annual Meeting of ACL & the 4th IJCNLP of AFNLP,2009:692-700.
附中文参考文献：
［13］王晶晶,李寿山,黄磊.中文微博用户性别分类方法研究［J］.中文信息学报,2014,28(6): 150-155.
［16］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.