面向高校学生微博的跨粒度情感分析
|
摘要
传统的微博情感分析通常会忽略不带感情色彩的情感词对微博情感的影响,并缺乏对复杂句式的分析。因此提出了一种结合条件随机场(conditional random filed,CRF)和复杂句式的跨粒度情感分析方法。该方法在CRF模型的基础上,融合复杂句式特征和语义依存特征,对学生微博进行细粒度情感分析,识别出微博文本中的情感要素。在此基础上,通过基于复杂句式的粗粒度情感分析方法分析微博文本的情感倾向,实现对学生总体情感倾向的跨粒度分析。实验结果显示,跨粒度情感分析方法的提出,使得情感要素识别的综合准确率达到了88%左右,微博情感分析的综合准确率达到了87%左右。比起传统的情感分析方法,准确率更高,分类效果更好。
Traditional sentiment analysis of micro-blog often ignore the influence of sentiment words without sentimental color on micro-blog sentiment,and lack of analysis for complex sentence. To solve the problem,this paper proposed a method of cross-grained sentiment analysis based on conditional random filed and complex sentence,which fused complex sentence and semantic dependency features on the basis of CRF. It could identify sentiment elements by analyzing microblog sentiment in fine-grained. It used the method of coarse-grained sentiment analysis based on complex sentence analyze sentimental tendency of student microblog. Finally,the experimental results show that the accuracy on sentiment elements can reach 88%,furthermore,the accuracy of microblog sentimental tendency can reach 87%. Compare to traditional method,the proposed method has higher accuracy and better performance.
Traditional sentiment analysis of micro-blog often ignore the influence of sentiment words without sentimental color on micro-blog sentiment,and lack of analysis for complex sentence. To solve the problem,this paper proposed a method of cross-grained sentiment analysis based on conditional random filed and complex sentence,which fused complex sentence and semantic dependency features on the basis of CRF. It could identify sentiment elements by analyzing microblog sentiment in fine-grained. It used the method of coarse-grained sentiment analysis based on complex sentence analyze sentimental tendency of student microblog. Finally,the experimental results show that the accuracy on sentiment elements can reach 88%,furthermore,the accuracy of microblog sentimental tendency can reach 87%. Compare to traditional method,the proposed method has higher accuracy and better performance.
引文
[1]肖江,丁星,何荣杰.基于领域情感词典的中文微博情感分析[J].电子设计工程,2015,23(12):18-21.(Xiao Jiang,Ding Xing,He Rongjie. Analysis of Chinese micro-blog emotion which based on field of emotional dictionary[J]. Electronic Design Engineering,2015,23(12):18-21.)
[2]陈晓东.基于情感词典的中文微博情感倾向分析研究[D].武汉:华中科技大学,2012.(Chen Xiaodong. Research on sentiment dictionary based emotional tendency analysis of Chinese micro blog[D].Wuhang:Huazhong University of Science and Technology,2012.)
[3] Catal C,Nangir M. A sentiment classification model based on multiple classifiers[J]. Applied Soft Computing,2017,50(1):135-141.
[4] Liu Shenghua,Li Fuxin,Li Fangtao,et al. Adaptive co-training SVM for sentiment classification on tweets[C]//Proc of ACM International Conference on Information&Knowledge Management. New York:ACM Press,2013:2079-2088.
[5] Hu Minqing,Liu Bing. Mining and summarizing customer reviews[C]//Proc of KDD. New York:ACM Press,2004:168-177.
[6]赵文婧.产品描述词及情感词抽取模式的研究[D].北京:北京邮电大学,2010.(Zhao Wenjing. Research on extraction patterns of product description words and sentiment words[D]. Beijing:Beijing University of Posts and Telecommunications,2010.)
[7] Xu Ruifeng,Wong K F,Xia Yunqing. Opinmine-opinion analysis system by CUHK for NTCIR-6 pilot task[C]//Proc of NTCIR. 2007:350-357.
[8]李阳辉,谢明,易阳.基于深度学习的社交网络平台细粒度情感分析[J].计算机应用研究,2017,34(3):743-747.(Li Yanghui,Xie Ming,Yi Yang. Fine-grained sentiment analysis for social network platform based on deep-learning model[J]. Application Research of Computers,2017,34(3):743-747.)
[9] Jin Wei,Ho H H. A novel lexicalized HMM-based learning framework for Web opinion mining[C]//Proc of the 26th Annual International Conference on Machine Learning. New York:ACM Press,2009:465-472.
[10] Liu Pengfei,Meng Helen. Seem Go:conditional random fields labeling and maximum entropy classification for aspect based sentiment analysis[C]//Proc of International Workshop on Semantic Evaluation. 2014:527-531.
[11]Lafferty J,Mc Callum A,Pereira F. Conditional random fields:probabilistic models for segmenting and labeling sequence data[C]//Proc of the 18th International Conference on Machine Learning. San Francisco:Morgan Kaufmann Publishing,2001:282-289.
[12]赵龙,郭立,谢锦生.条件随机场模型的场景描述[J].中国图象图形学报,2013,18(3):271-276.(Zhao Long,Guo Li,Xie Jinsheng. Scene description based on the conditional random fields model[J]. Journal of Image and Graphics,2013,18(3):271-276.)
[13]刘丽,王永恒,韦航.面向产品评论的细粒度情感分析[J].计算机应用,2015,35(12):3481-3486.(Liu Li,Wang Yongheng,Wei Hang. Fine-grained sentiment analysis oriented to product comment[J]. Journal of Computer Applications,2015,35(12):3481-3486.)
[14]邸鹏,李爱萍,段利国.基于转折句式的文本情感倾向性分析[J].计算机工程与设计,2014,35(12):4289-4295.(Di Peng,Li Aiping,Duan Liguo. Text sentiment polarity analysis based on transition sentence[J]. Computer Engineering and Design,2014,35(12):4289-4295.)
[15]邸鹏,段利国.基于复杂句式的文本情感倾向性分析[J].计算机应用与软件,2015,32(11):57-61.(Di Peng,Duan Liguo. Text sentiment polarity analysis based on complex sentences[J]. Computer Applications and Software,2015,32(11):57-61.)
[2]陈晓东.基于情感词典的中文微博情感倾向分析研究[D].武汉:华中科技大学,2012.(Chen Xiaodong. Research on sentiment dictionary based emotional tendency analysis of Chinese micro blog[D].Wuhang:Huazhong University of Science and Technology,2012.)
[3] Catal C,Nangir M. A sentiment classification model based on multiple classifiers[J]. Applied Soft Computing,2017,50(1):135-141.
[4] Liu Shenghua,Li Fuxin,Li Fangtao,et al. Adaptive co-training SVM for sentiment classification on tweets[C]//Proc of ACM International Conference on Information&Knowledge Management. New York:ACM Press,2013:2079-2088.
[5] Hu Minqing,Liu Bing. Mining and summarizing customer reviews[C]//Proc of KDD. New York:ACM Press,2004:168-177.
[6]赵文婧.产品描述词及情感词抽取模式的研究[D].北京:北京邮电大学,2010.(Zhao Wenjing. Research on extraction patterns of product description words and sentiment words[D]. Beijing:Beijing University of Posts and Telecommunications,2010.)
[7] Xu Ruifeng,Wong K F,Xia Yunqing. Opinmine-opinion analysis system by CUHK for NTCIR-6 pilot task[C]//Proc of NTCIR. 2007:350-357.
[8]李阳辉,谢明,易阳.基于深度学习的社交网络平台细粒度情感分析[J].计算机应用研究,2017,34(3):743-747.(Li Yanghui,Xie Ming,Yi Yang. Fine-grained sentiment analysis for social network platform based on deep-learning model[J]. Application Research of Computers,2017,34(3):743-747.)
[9] Jin Wei,Ho H H. A novel lexicalized HMM-based learning framework for Web opinion mining[C]//Proc of the 26th Annual International Conference on Machine Learning. New York:ACM Press,2009:465-472.
[10] Liu Pengfei,Meng Helen. Seem Go:conditional random fields labeling and maximum entropy classification for aspect based sentiment analysis[C]//Proc of International Workshop on Semantic Evaluation. 2014:527-531.
[11]Lafferty J,Mc Callum A,Pereira F. Conditional random fields:probabilistic models for segmenting and labeling sequence data[C]//Proc of the 18th International Conference on Machine Learning. San Francisco:Morgan Kaufmann Publishing,2001:282-289.
[12]赵龙,郭立,谢锦生.条件随机场模型的场景描述[J].中国图象图形学报,2013,18(3):271-276.(Zhao Long,Guo Li,Xie Jinsheng. Scene description based on the conditional random fields model[J]. Journal of Image and Graphics,2013,18(3):271-276.)
[13]刘丽,王永恒,韦航.面向产品评论的细粒度情感分析[J].计算机应用,2015,35(12):3481-3486.(Liu Li,Wang Yongheng,Wei Hang. Fine-grained sentiment analysis oriented to product comment[J]. Journal of Computer Applications,2015,35(12):3481-3486.)
[14]邸鹏,李爱萍,段利国.基于转折句式的文本情感倾向性分析[J].计算机工程与设计,2014,35(12):4289-4295.(Di Peng,Li Aiping,Duan Liguo. Text sentiment polarity analysis based on transition sentence[J]. Computer Engineering and Design,2014,35(12):4289-4295.)
[15]邸鹏,段利国.基于复杂句式的文本情感倾向性分析[J].计算机应用与软件,2015,32(11):57-61.(Di Peng,Duan Liguo. Text sentiment polarity analysis based on complex sentences[J]. Computer Applications and Software,2015,32(11):57-61.)
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |