面向微博的中文反语识别研究

J4 ›› 2015, Vol. 37 ›› Issue (12): 2312-2317.

面向微博的中文反语识别研究

邓钊1，贾修一1，陈家骏2

（1.南京理工大学计算机科学与工程学院，江苏南京 210094；2.南京大学计算机科学与技术系，江苏南京 210023）

收稿日期:2015-08-28 修回日期:2015-10-26 出版日期:2015-12-25 发布日期:2015-12-25
基金资助:
国家自然科学基金资助项目（61403200）；江苏省自然科学基金资助项目（BK20140800）

Research on Chinese irony detection in microblog

DENG Zhao1,JIA Xiuyi1,CHEN Jiajun2

（1.School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094;2.Department of Computer Science and Technology,Nanjing University,Nanjing 210023,China）

Received:2015-08-28 Revised:2015-10-26 Online:2015-12-25 Published:2015-12-25

摘要/Abstract

摘要：

反语识别已成为当前研究的热点，但当前对于中文反语识别研究报道较少。针对于此，主要研究面向社交网络的中文反语识别。在借鉴外文相关工作的基础上，结合中文语言和社交网络的特性，构建了六种特征，通过信息增益对比了各种特征有效性，并检测了不同分类器在该特征体系中的稳定性。实验结果表明，本文构建的特征在识别反语的任务中有显著的效果。

关键词: 反语识别, 特征构建, 微博

Abstract:

Irony detection has drawn much attention in recent years. However, most studies are based on foreign languages. In this paper, we focus on the Chinese irony detection in microblog. Considering the characteristics of both Chinese language and social networks, we build a set of discriminating features for Chinese irony detection. Information gain is applied to these six features to compare their efficiency, and several classifiers are employed to test their stability. Experimental results prove the efficiency of the proposed features.

Key words: irony detection;feature construction;microblog

邓钊1，贾修一1，陈家骏2. 面向微博的中文反语识别研究[J]. J4, 2015, 37(12): 2312-2317.

DENG Zhao1,JIA Xiuyi1,CHEN Jiajun2. Research on Chinese irony detection in microblog [J]. J4, 2015, 37(12): 2312-2317.

参考文献

［1］Tang Y J,Chen H.Chinese irony corpus construction and ironic structure analysis［C］∥Proc of the 25th International Conference on Computational Linguistics:Technical Papers,2014:12691278．
［2］Liu Zhengguang. A critique of irony theories［J］. Journal of PLA University of Foreign Language,2002，22（4）:1618．(in Chinese)
［3］Gibbs R W,Colston H L.Irony in language and thought:A cognitive science reader［M］.New York:Lawrence Erlbaum Associates,2007．
［4］Utsumi A. A unified theory of irony and its computational formalization［C］∥International Conference on Computational Linguistics,1996:962967．
［5］Xiang Li.Irony illustrated:A crosscultural exploration of situational irony in China and the United States［M］.New York:SinoPlatonic Papers，2008．
［6］GonzlezIbez R,Muresan S,Wacholder N.Identifying sarcasm in Twitter:A closer look［C］∥Proc of the 49th Annual Meeting of the Association for Computational Linguistics,2011:581586．
［7］Reyes A,Rosso P,Buscaldi D.From humor recognition to irony detection:The figurative language of social media［J］.Data & Knowledge Engineering,2012,74（3）:112．
［8］Reyes A,Rosso P,Veale T.A multidimensional approach for detecting irony in Twitter［J］.Language Resources & Evaluation,2013,47（1）:239268．
［9］Reyes A,Rosso P.Making objective decisions from subjective data:Detecting irony in customer reviews［J］.Decision Support Systems,2012,53（4）:754760．
［10］Burfoot C, Baldwin T, Burfoot C. Automatic satire detection:Are you having a laugh？［C］∥Proc of the Joint Conference of the 47th Annual Meeting of the ACL,2009:161164．
［11］Vanin A A， Freitas L A， Vieira R, et al. Some clues on irony detection in tweets［C］∥WWW 2013 Companion,ACM 9781450320382,2013:635636．
［12］Francesco B,Francesco R,Horacio S.Italian irony detection in Twitter:A first approach［C］∥Proc of the 1st Conference on Computational Linguistics,2014:2832．
［13］Tsur O,Davidov D.Icwsma great catchy name:Semisupervised recognition of sarcastic sentences in product reviews［C］∥Proc of the International AAAI Conference on Weblogs & Social, 2010:162169．
［14］Davidov D,Tsur O.Semisupervised recognition of sarcastic sentences in Twitter and Amazon［C］∥Proc of the 14th Conference on Computational Natural Language Learning,2010:107116．
［15］Carvalho P，Sarmento L.Clues for detecting irony in usergenerated contents:oh...!! it’s "so easy" ;）［C］∥Proc of the 1st International CIKM Workshop on TopicSentiment Analysis for Mass Opinion Measurement(TSA’09),2009:5356．
［16］Zhang Lin, Qian Guanqun,Fan Weiguo,et al.Sentiment analysis based on light reviews［J］.Journal of Software,2014，25（12）:27902807.（in Chinese）
［17］Saif M,Dunne C,Bonnie D.Generating highcoverage semantic orientation lexicons from overtly marked words and a thesaurus ［C］∥Proc of the 2009 Conference on EMNLP,2009:599608．
附中文参考文献：
［2］刘正光.反语理论综述［J］.解放军外国语学院学报,2002，22（4）:1618．
［16］张林,钱冠群,樊卫国,等.轻型评论的情感分析研究［J］.软件学报,2014,25（12）:27902807．

[1]	段玲, 郭军军, 余正涛, 相艳, . 基于正文和评论交互注意的微博案件方面识别[J]. 计算机工程与科学, 2022, 44(06): 1097-1104.
[2]	王春东, 张卉, 莫秀良, 杨文军. 微博情感分析综述[J]. 计算机工程与科学, 2022, 44(01): 165-175.
[3]	蔡晨1,2，罗可1,2 . 融合BTM和图论的微博检索模型[J]. 计算机工程与科学, 2019, 41(08): 1512-1518.
[4]	高永兵1,宋添树1,2,李江宇1,马占飞3. 基于知网的个人微博语义相关度的聚类研究[J]. 计算机工程与科学, 2019, 41(06): 1128-1135.
[5]	邱云飞，陈昂. 微博社区的动态节点自适应增量交互优化[J]. 计算机工程与科学, 2019, 41(02): 370-377.
[6]	谢修娟1,李香菊1，莫凌飞2. 基于改进K-means算法的微博舆情分析研究[J]. 计算机工程与科学, 2018, 40(01): 155-158.
[7]	张迪，马慧芳，贾俊杰，余丽. 一种基于标签概率相关性的微博推荐方法[J]. 计算机工程与科学, 2017, 39(09): 1742-1748.
[8]	郑伟涛1，吴永亮1，郭芳琳1，闫光辉1，何力2. 基于链接分析和用户兴趣的微博社区发现算法[J]. 计算机工程与科学, 2017, 39(04): 804-812.
[9]	刘莉平，刘梦，李绍鹏. 基于情感分析的新浪微博争议度分析[J]. 计算机工程与科学, 2016, 38(10): 2158-2164.
[10]	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, 2016, 38(09): 1917-1923.
[11]	高永兵，钟振华，王宇，马占飞. 基于混合方法的中文微博自动摘要技术研究[J]. J4, 2016, 38(06): 1257-1261.
[12]	黄贤英,陈红阳,刘英涛,熊李媛. 一种新的微博短文本特征词选择算法[J]. J4, 2015, 37(09): 1761-1767.
[13]	张岩峰1,陈长松1,杨涛1，左俐俐2，丁飞1. 微博用户的个性分类分析[J]. J4, 2015, 37(02): 402-409.
[14]	王金辉，贺利坚，张伟,童向荣. 微博中基于用户偏好的信息传播研究 [J]. J4, 2013, 35(3): 140-144.
[15]	汪祥1,贾焰1,周斌1,陈儒华1,韩毅2. 基于交互关系的微博用户标签预测[J]. J4, 2013, 35(10): 44-50.