微博情感分析的情感词典构造及分析方法研究
|
摘要
为了提高微博情感分析的准确性,对微博情感分析中的语义规则和情感词典进行了研究。在传统基于情感词典的微博情感分析的基础上对情感词典中的微博情感词典的构造方法做了改进。首先构造情感词典,主要包括开源情感词典、具有时代特征的网络情感词典、根据情感词的位置特点构造的微博情感词典、具有明显情感倾向的语气情感词典。在词典构造完成的基础上结合中文语法规则,主要包括句间关系规则和句型关系规则,根据句间和句型关系算法计算微博句子的情感倾向性,将微博文本分为正向、负向和中性三个方面。为了提高微博分类的准确率,提出构建语气词词典,并且在语气词权重计算的方法上做出创新,同时对微博情感词典的构造方法做出了改进。实验结果表明,该方法能够提高微博情感分析的正确率。
In order to improve the accuracy of micro-blog sentiment analysis,semantic rules and sentiment dictionary in micro-blog sentiment analysis are studied.The constructing method of micro-blog sentiment dictionary in sentiment dictionary is improved on the basis of the traditional sentiment analysis based on sentiment dictionary.First of all,we construct the sentiment dictionary including the opensource sentiment dictionary,the net sentiment dictionary with the characteristics of the times,micro-blog sentiment dictionary based on position of emotional words on the basis of constructed dictionaries,and motional sentiment dictionary with obvious emotion tendency.Based on the completion of the construction of the lexicon,combined with the Chinese grammar rules,including the rule of relationship between sentences and rules of sentence patterns,the sentiment tendencies of Weibo sentences are calculated according to algorithm of relationship between sentences and sentence patterns.The micro-blog texts are divided into three categories:positive,negative and neutral section.In order to improve the classification accuracy,we propose to construct a modal dictionaries and make innovations in the modal weight calculation of the modal particles.At the same time,the construction method of the micro-blog sentiment dictionary is improved.Experiment shows that this method can improve the accuracy of the emotional analysis of micro-blog.
In order to improve the accuracy of micro-blog sentiment analysis,semantic rules and sentiment dictionary in micro-blog sentiment analysis are studied.The constructing method of micro-blog sentiment dictionary in sentiment dictionary is improved on the basis of the traditional sentiment analysis based on sentiment dictionary.First of all,we construct the sentiment dictionary including the opensource sentiment dictionary,the net sentiment dictionary with the characteristics of the times,micro-blog sentiment dictionary based on position of emotional words on the basis of constructed dictionaries,and motional sentiment dictionary with obvious emotion tendency.Based on the completion of the construction of the lexicon,combined with the Chinese grammar rules,including the rule of relationship between sentences and rules of sentence patterns,the sentiment tendencies of Weibo sentences are calculated according to algorithm of relationship between sentences and sentence patterns.The micro-blog texts are divided into three categories:positive,negative and neutral section.In order to improve the classification accuracy,we propose to construct a modal dictionaries and make innovations in the modal weight calculation of the modal particles.At the same time,the construction method of the micro-blog sentiment dictionary is improved.Experiment shows that this method can improve the accuracy of the emotional analysis of micro-blog.
引文
[1]TURNEY P D.Thumbs up or thumbs down?:semantic orientation applied to unsupervised classification of reviews[C]//Proceedings of the 40th annual meeting on association for computational linguistics.Philadelphia,Pennsylvania:ACM,2002:417-424.
[2]CUI Hang,MITTAL V,DATAR M.Comparative experiments on sentiment classification for online product reviews[C]//Proceedings of the 21st national conference on artificial intelligence.Boston,Massachusetts,USA:AAAI Press,2006:1265-1270.
[3]王伟,周咏梅,阳爱民,等.一种基于LDA主题模型的评论文本情感分类方法[J].数据采集与处理,2017,32(3):629-635.
[4]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.
[5]TABOADA M,BROOKE J,TOFILOSKI M,et al.Lexiconbased methods for sentiment analysis[J].Computational Linguistics,2011,37(2):267-307.
[6]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.
[7]周剑峰,阳爱民,周咏梅.基于中文微博的情感词典构建及分类方法[J].计算机与数字工程,2014,42(10):1773-1776.
[8]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.
[9]王志涛,於志文,郭斌,等.基于词典和规则集的中文微博情感分析[J].计算机工程与应用,2015,51(8):218-225.
[10]王振宇,吴泽衡,胡方涛.基于HowNet和PMI的词语情感极性计算[J].计算机工程,2012,38(15):187-189.
[11]刘培玉,张艳辉,朱振方,等.融合表情符号的微博文本倾向性分析[J].山东大学学报:理学版,2014,49(11):8-13.
[12]朱嫣岚,闵锦,周雅倩,等.基于HowNet的词汇语义倾向计算[J].中文信息学报,2006,20(1):14-20.
[13]陈建美,林鸿飞,杨志豪.基于语法的情感词汇自动获取[J].智能系统学报,2009,4(2):100-106.
[14]姜杰,夏睿.机器学习与语义规则融合的微博情感分类方法[J].北京大学学报:自然科学版,2017,53(2):247-254.
[15]WHITELAW C,GARG N,ARGAMON S.Using appraisal groups for sentiment analysis[C]//Proceedings of the 14th ACM international conference on information and knowledge management.Bremen,Germany:ACM,2005:625-631.
[16]LIU Bing.Sentiment analysis and opinion mining[J].Synthesis Lectures on Human Language Technologies,2016,30(1):152-153.
[17]赵天奇,姚海鹏,方超,等.语义规则与表情加权融合的微博情感分析方法[J].重庆邮电大学学报:自然科学版,2016,28(4):503-510.
[18]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.
[19]刘楠.面向微博短文本的情感分析研究[D].武汉:武汉大学,2013.
[2]CUI Hang,MITTAL V,DATAR M.Comparative experiments on sentiment classification for online product reviews[C]//Proceedings of the 21st national conference on artificial intelligence.Boston,Massachusetts,USA:AAAI Press,2006:1265-1270.
[3]王伟,周咏梅,阳爱民,等.一种基于LDA主题模型的评论文本情感分类方法[J].数据采集与处理,2017,32(3):629-635.
[4]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.
[5]TABOADA M,BROOKE J,TOFILOSKI M,et al.Lexiconbased methods for sentiment analysis[J].Computational Linguistics,2011,37(2):267-307.
[6]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.
[7]周剑峰,阳爱民,周咏梅.基于中文微博的情感词典构建及分类方法[J].计算机与数字工程,2014,42(10):1773-1776.
[8]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.
[9]王志涛,於志文,郭斌,等.基于词典和规则集的中文微博情感分析[J].计算机工程与应用,2015,51(8):218-225.
[10]王振宇,吴泽衡,胡方涛.基于HowNet和PMI的词语情感极性计算[J].计算机工程,2012,38(15):187-189.
[11]刘培玉,张艳辉,朱振方,等.融合表情符号的微博文本倾向性分析[J].山东大学学报:理学版,2014,49(11):8-13.
[12]朱嫣岚,闵锦,周雅倩,等.基于HowNet的词汇语义倾向计算[J].中文信息学报,2006,20(1):14-20.
[13]陈建美,林鸿飞,杨志豪.基于语法的情感词汇自动获取[J].智能系统学报,2009,4(2):100-106.
[14]姜杰,夏睿.机器学习与语义规则融合的微博情感分类方法[J].北京大学学报:自然科学版,2017,53(2):247-254.
[15]WHITELAW C,GARG N,ARGAMON S.Using appraisal groups for sentiment analysis[C]//Proceedings of the 14th ACM international conference on information and knowledge management.Bremen,Germany:ACM,2005:625-631.
[16]LIU Bing.Sentiment analysis and opinion mining[J].Synthesis Lectures on Human Language Technologies,2016,30(1):152-153.
[17]赵天奇,姚海鹏,方超,等.语义规则与表情加权融合的微博情感分析方法[J].重庆邮电大学学报:自然科学版,2016,28(4):503-510.
[18]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.
[19]刘楠.面向微博短文本的情感分析研究[D].武汉:武汉大学,2013.
© 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 |