基于主题模型的微博评论方面观点褒贬态度挖掘
|
摘要
在新浪微博中,原创微博下存在着很多用户评论。这些评论能反映原创微博的内容,用户的态度以及与其相关的一些话题。因此,对这些评论进行细粒度信息的提取与褒贬态度的分类很有必要。基于上述原因,该文首先提出与原创无关的评论判别方法,通过三个相似度方法得到原创微博与评论之间的相关度,从而判断评论对象是否为原创微博。其次,提出一种用于评论集褒贬态度和方面观点挖掘的新模型,该模型在LDA中加入了表情符号层与文本情感层,实现评论集方面和褒贬态度的同步检测。实验表明:表情符号情感层的融入能提高新模型褒贬态度识别能力。
In microblogging site,the comments under the original microblog reflect the original microblog's content,users' attitudes and certain related topics.To extract fine-grained information and affective meaning from those comments,we first propose to detect if a comment is targeted towards the microblog itself using three similarity methods.Then,a novel model is proposed for mining aspect-based opinion and affective meaning in microblogging comments.This model introduces emoticon sentiment and textual sentiment into LDA inference framework and achieves synchronized detection of aspect and affective meaning in comments.Experimental results demonstrate that the emoticon sentiment layer can improve the affective meaning recognition results.
In microblogging site,the comments under the original microblog reflect the original microblog's content,users' attitudes and certain related topics.To extract fine-grained information and affective meaning from those comments,we first propose to detect if a comment is targeted towards the microblog itself using three similarity methods.Then,a novel model is proposed for mining aspect-based opinion and affective meaning in microblogging comments.This model introduces emoticon sentiment and textual sentiment into LDA inference framework and achieves synchronized detection of aspect and affective meaning in comments.Experimental results demonstrate that the emoticon sentiment layer can improve the affective meaning recognition results.
引文
[1]Quan C Q,Ren F J.A blog emotion corpus for emotional expression analysis inChinese[J].Computer Speech and Language,2010,24(4):726-749.
[2]Li J,Ren F J.Emotionrecognition of weblog sentences based on an ensemble algorithm of multi-label classification and word emotions[J].IEEJ Transactions on E-lectronics Information and Systems,2012,132(8):1362-1375.
[3]黄发良,于戈,张继连,等.基于社交关系的微博主题情感挖掘[J].软件学报,2017,28(3):694-707.
[4]Ren F J,Kang X.Employing hierarchicalbayesian networks in simple and complex emotion topic analysis[J].Computer Speech and Language,2013,27(4):943-968.
[5]Moghaddam S,Ester M.On the design of LDA models for aspect-based opinion mining[C]//Proceedings of the 21st ACM International Conference on Information and Knowledge Management.ACM,2012:803-812.
[6]Lin C,He Y.Joint sentiment/topic model for sentiment analysis[C]//Proceedings of the 18th ACM International Conference on Information and Knowledge Management.ACM,2009:375-384.
[7]Jo Y,Oh A H.Aspect and sentiment unification model for online review analysis[C]//Proceedings of the 4th ACM International Conference on Web Search and Data Mining.ACM,2011:815-824.
[8]黄发良,冯时,王大玲,等.基于多特征融合的微博主题情感挖掘[J].计算机学报,2017,40(4):872-888.
[9]Ren F J,Wu Y,Predictinguser-topic opinions in twitter with social and topical context[J].IEEE Transactions on Affective Computing,2013,4(4):412-424.
[10]Quan C Q,Ren F J.Unsupervised product feature extraction for feature-oriented opinion determination[J].Information Sciences,2014,272:16-28.
[11]Kim S M,Hovy E.Determining the sentiment of opinions[C]//Proceedings of the 20th International Conference on Computational Linguistics.Association for Computational Linguistics,2004:1367.
[12]Hu M,Liu B.Mining and summarizing customer reviews[C]//Proceedings of the 10th ACM SIGKDDInternational Conference on Knowledge Discovery and Data Mining,ACM,2004:168-177.
[13]Zhou X,Wan X,Xiao J.CMiner:Opinion extraction and summarization for Chinese microblogs[J].IEEETransactions on Knowledge and Data Engineering,2016,28(7):1650-1663.
[14]Blei D M,Ng A Y,Jordan M I.Latent dirichlet allocation[J].Journal ofMachine Learning Research,2003,3(Jan):993-1022.
[15]Titov I,Mcdonald R.A joint model of text and aspect ratings for sentiment summarization[C]//Proceedings of ACL-08:HLT,2008:308-316.
[16]李晨曦,谢罗迪.基于LDA模型的文本分类与观点挖掘[J].电子技术与软件工程,2017,04:209-210.
[17]谢丽星.基于SVM的中文微博情感分析的研究[D].北京:清华大学硕士学位论文,2011.
[18]Zhang L,Pei S,Deng L,et al.Microblog sentiment analysis based on emoticon networks model[C]//Proceeding of the 5th International Conference on Internet Multimedia Computing and Service.ACM,2013:134-138.
[19]张华平,李恒训,李清敏.情感词发现与极性权重自动计算算法研究[J].中文信息学报,2017,31(3):48-54.
[20]Zhang Q,Ren F J,Kang X,et al.Building emotional corpus for microblogging emoticons[J].International Journal of Advanced Intelligence,2017,9(03):381-395.
[21]Jiang F,Liu Y Q,Luan H B,et al.Microblog sentiment analysis with emoticon space model[J].Journal of Computer Science and Technology,2015,30(5):1120-1129.
[22]Liu K L,Li W J,GuoM.Emoticon smoothed language models for twitter sentiment analysis[C]//Proceedings of the 26th AAAI Conference on Artificial Intelligence.2012:1678-1684.
[23]Churches O,Nicholls M,Thiessen M,et al.Emoticons in mind:an event-related potential study[J].Social Neuroscience,2014,9(2):196-202.
[2]Li J,Ren F J.Emotionrecognition of weblog sentences based on an ensemble algorithm of multi-label classification and word emotions[J].IEEJ Transactions on E-lectronics Information and Systems,2012,132(8):1362-1375.
[3]黄发良,于戈,张继连,等.基于社交关系的微博主题情感挖掘[J].软件学报,2017,28(3):694-707.
[4]Ren F J,Kang X.Employing hierarchicalbayesian networks in simple and complex emotion topic analysis[J].Computer Speech and Language,2013,27(4):943-968.
[5]Moghaddam S,Ester M.On the design of LDA models for aspect-based opinion mining[C]//Proceedings of the 21st ACM International Conference on Information and Knowledge Management.ACM,2012:803-812.
[6]Lin C,He Y.Joint sentiment/topic model for sentiment analysis[C]//Proceedings of the 18th ACM International Conference on Information and Knowledge Management.ACM,2009:375-384.
[7]Jo Y,Oh A H.Aspect and sentiment unification model for online review analysis[C]//Proceedings of the 4th ACM International Conference on Web Search and Data Mining.ACM,2011:815-824.
[8]黄发良,冯时,王大玲,等.基于多特征融合的微博主题情感挖掘[J].计算机学报,2017,40(4):872-888.
[9]Ren F J,Wu Y,Predictinguser-topic opinions in twitter with social and topical context[J].IEEE Transactions on Affective Computing,2013,4(4):412-424.
[10]Quan C Q,Ren F J.Unsupervised product feature extraction for feature-oriented opinion determination[J].Information Sciences,2014,272:16-28.
[11]Kim S M,Hovy E.Determining the sentiment of opinions[C]//Proceedings of the 20th International Conference on Computational Linguistics.Association for Computational Linguistics,2004:1367.
[12]Hu M,Liu B.Mining and summarizing customer reviews[C]//Proceedings of the 10th ACM SIGKDDInternational Conference on Knowledge Discovery and Data Mining,ACM,2004:168-177.
[13]Zhou X,Wan X,Xiao J.CMiner:Opinion extraction and summarization for Chinese microblogs[J].IEEETransactions on Knowledge and Data Engineering,2016,28(7):1650-1663.
[14]Blei D M,Ng A Y,Jordan M I.Latent dirichlet allocation[J].Journal ofMachine Learning Research,2003,3(Jan):993-1022.
[15]Titov I,Mcdonald R.A joint model of text and aspect ratings for sentiment summarization[C]//Proceedings of ACL-08:HLT,2008:308-316.
[16]李晨曦,谢罗迪.基于LDA模型的文本分类与观点挖掘[J].电子技术与软件工程,2017,04:209-210.
[17]谢丽星.基于SVM的中文微博情感分析的研究[D].北京:清华大学硕士学位论文,2011.
[18]Zhang L,Pei S,Deng L,et al.Microblog sentiment analysis based on emoticon networks model[C]//Proceeding of the 5th International Conference on Internet Multimedia Computing and Service.ACM,2013:134-138.
[19]张华平,李恒训,李清敏.情感词发现与极性权重自动计算算法研究[J].中文信息学报,2017,31(3):48-54.
[20]Zhang Q,Ren F J,Kang X,et al.Building emotional corpus for microblogging emoticons[J].International Journal of Advanced Intelligence,2017,9(03):381-395.
[21]Jiang F,Liu Y Q,Luan H B,et al.Microblog sentiment analysis with emoticon space model[J].Journal of Computer Science and Technology,2015,30(5):1120-1129.
[22]Liu K L,Li W J,GuoM.Emoticon smoothed language models for twitter sentiment analysis[C]//Proceedings of the 26th AAAI Conference on Artificial Intelligence.2012:1678-1684.
[23]Churches O,Nicholls M,Thiessen M,et al.Emoticons in mind:an event-related potential study[J].Social Neuroscience,2014,9(2):196-202.