期刊文献+

基于改进TF-IDF与BERT的领域情感词典构建方法 被引量:1

Construction Method of Domain Sentiment Lexicon Based on Improved TF-IDF and BERT
下载PDF
导出
摘要 领域情感词典的构建是领域文本情感分析的基础。现有的领域情感词典构建方法存在所筛选候选情感词冗余度高、情感极性判断失准、领域依赖性强等问题。为了提高所筛选候选情感词的领域性和判断领域情感词极性的准确程度,提出了一种基于改进词频-逆文档频率(TF-IDF)与BERT的领域情感词典构建方法。该方法在筛选领域候选情感词阶段对TF-IDF算法进行改进,将隐含狄利克雷分布(LDA)算法与改进后的TF-IDF算法结合,进行领域性修正,提升了所筛选候选情感词的领域性;在候选情感词极性判断阶段,将情感倾向点互信息算法(SO-PMI)与BERT结合,利用领域情感词微调BERT分类模型,提高了判断领域候选情感词情感极性的准确程度。在不同领域的用户评论数据集上进行实验,结果表明,该方法可以提高所构建领域情感词典的质量,使用该方法构建的领域情感词典用于汽车领域和手机领域文本情感分析的F1值分别达到78.02%和88.35%。 The construction of a domain sentiment lexicon is the foundation of domain text sentiment analysis.The existing me-thods for constructing domain sentiment lexicon have problems such as high redundancy of selected candidate sentiment words,inaccurate judgment of sentiment polarity,and high domain dependency.In order to improve the domain specificity of selected candidate sentiment words and the accuracy of judging the polarity of domain sentiment words,a domain sentiment lexicon construction method based on improved term frequency-inverse document frequency(TF-IDF)and BERT is proposed.This method improves the TF-IDF algorithm in the phase of selecting domain candidate sentiment words.The latent dirichlet allocation(LDA)algorithm is combined with the improved TF-IDF algorithm to perform domain corrections,improves the domain specificity of the selected candidate sentiment words.In the polarity judgment stage of candidate sentiment words,the semantic orientation pointwise mutual information(SO-PMI)algorithm is combined with BERT.By fine-tuning the BERT classification model using domain sentiment words,the accuracy of judging the sentiment polarity of domain candidate sentiment words is improved.Experiments are conducted on user comment datasets in different domains,and the experimental results show that this method can improve the quality of the constructed domain sentiment lexicon,and the F1 value of the domain sentiment lexicon constructed by this method for text sentiment analysis in the automotive field and mobile phone field reaches 78.02%and 88.35%,respectively.
作者 蒋昊达 赵春蕾 陈瀚 王春东 JIANG Haoda;ZHAO Chunlei;CHEN Han;WANG Chundong(Key Laboratory of Computer Vision and System of Ministry of Education,Tianjin University of Technology,Tianjin 300384,China;Tianjin Key Laboratory of Intelligent Computing and Novel Software Technology,Tianjin 300384,China)
出处 《计算机科学》 CSCD 北大核心 2024年第S01期150-158,共9页 Computer Science
基金 国家重点研发计划“科技助力经济2020”重点专项项目(SQ2020YFF0413781,SQ2020YFF0401503)。
关键词 情感分析 领域情感词典 词频-逆文档频率 隐含狄利克雷分布 情感倾向点互信息算法 BERT模型 Sentiment analysis Domain sentiment lexicon Term Frequency-Inverse Document Frequency(TF-IDF) Latent Dirichlet allocation(LDA) Semantic orientation pointwise mutual information(SO-PMI) BERT model
  • 相关文献

参考文献7

二级参考文献118

  • 1朱嫣岚,闵锦,周雅倩,黄萱菁,吴立德.基于HowNet的词汇语义倾向计算[J].中文信息学报,2006,20(1):14-20. 被引量:326
  • 2Vasileios Hatzivassiloglou, Kathleen R. McKeown. Predicting the semantic orientation of adjectives[A]. In: Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and the 8th Conference of the European Chapter of the ACL[C], 1997:174- 181.
  • 3Turney, Peter, Littman Michael. Measuring praise and criticism: Inference of semantic orientation from association[J]. ACM Transactions on Information Systems, 2003, 21(4): 315- 346.
  • 4Turney ,Peter. Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews[A]. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics[C]. 2002:417 -424.
  • 5Bo Pang,Lillian Lee, Shivanathan Vaithyanathan. Thumbs up? Sentiment classification using machine learning techniques[A]. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing[C]. 2002:79 - 86.
  • 6Bo Pang,Lillian Lee. Seeing Stars: Exploiting Class Relationships for Sentiment Categorizalion with respect to Rating Seales[A]. ACL2005, 115-124.
  • 7K Dave, S lawrence, DM Pennock. , Mining the peanut gallery: opinion extraction and semantic classification of product reviews[A]. WWW2003, 519-28.
  • 8Bing Liu, Minqing Hu, Junsheng Cheng. Opinion observer: analyzing and comparing opinions on the Web[A].WWW2005, 324- 351.
  • 9HowNet[R]. HowNet's Home Page. http://www. keenage.com.
  • 10刘群 李素建.基于《知网》的词汇语义相似度的计算[A]..第三届汉语词汇语义学研讨会[C].台北,2002..

共引文献484

同被引文献6

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部