计算机科学 ›› 2015, Vol. 42 ›› Issue (6): 220-222.doi: 10.11896/j.issn.1002-137X.2015.06.046

• 人工智能 • 上一篇    下一篇

面向评论信息的跨领域词汇情感倾向判别方法

吴斐,张玉红,胡学钢   

  1. 合肥工业大学计算机与信息学院 合肥230009,合肥工业大学计算机与信息学院 合肥230009,合肥工业大学计算机与信息学院 合肥230009
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家高技术研究发展计划(863计划)(2012AA011005),国家自然科学基金(61273292,3),安徽省自然科学基金(1208085QF122)资助

Approach of Cross-domain Word Sentiment Orientation Identification on Reviews

WU Fei, ZHANG Yu-hong and HU Xue-gang   

  • Online:2018-11-14 Published:2018-11-14

摘要: 词汇的情感倾向判别对文本情感分类具有重要意义。已有方法多假设存在基准词,根据目标词与基准词的关联度来判别目标词的情感倾向。实际应用中,尤其是评论语料库中基准词往往存在情感歧义问题,从而影响判别结果的准确性。基于上述分析,面向给定语料库,提出一种基准词的提取和消歧方法,并在此基础上实现跨领域的词汇情感倾向判别。首先在任一标记语料库中自动提取候选基准词;然后基于共现矩阵评估并过滤部分具有情感歧义的基准词;最后通过计算基准词与目标词的相似性,实现目标词的情感倾向判别。实验结果表明了方法的有效性和可行性。

关键词: 基准词,PMI,跨领域,情感倾向,情感歧义

Abstract: The sentiment orientation identification for word is important for text sentiment classification.The existing efforts identify the sentiment orientation of target words according to the similarity of the target words and paradigm words with the assumption that there are some paradigm words.However,the ambiguity of emotion of paradigm words in different corpus affects the results of sentiment classification.We proposed a novel method for cross-domain word sentiment orientation identification based on extracting paradigm words and eliminating the ambiguity of paradigm words in the given corpus.More specifically,we first extracted the candidate paradigm words automatically in a labeled corpus,and then filtered the paradigm words those involve in ambiguity of emotion based on the co-occurrence matrix of paradigm words and target words in the target domain.Finally through computing the similarity of paradigm words and target words,we identified the sentiment orientation of target words.The experimental results demonstrate the effectiveness of our method.

Key words: Paradigm word,PMI,Cross-domain,Sentiment orientation,Ambiguity of emotion

[1] 王素格,李德玉,魏英杰,等.基于同义词的词汇情感倾向判别方法[J].中文信息学报,2009,23(5):68-74 Wang Su-ge,Li De-yu,Wei Ying-jie,et al.A Synonyms Based Word Sentiment Orientation Discriminating [J].Journal of Chinese Information Processing,2009,23(5):68-74
[2] Dai Liu-ling,Liu Bin,Xia Yu-ning.Measuring Semantic Similarity between Words Using HowNet[C]∥International Confe-rence on Computer Science and Information Technology.2008:601-605
[3] 朱嫣岚,阂锦,周雅倩,等.基于HowNet的词汇语义倾向计算[J].中文信息学报,2009,0(1):14-20 Zhu Yan-lan,Min Jin,Zhou Ya-qian,et al.Semantic Orientation Computing Based on HowNet [J].Journal of Chinese Information Processing,2009,0(1):14-20
[4] 赵妍妍,秦兵,刘挺.文本情感分析[J].Journal of Software,2010,1(8):1834-1848Zhao Yan-yan,Qin Bing,Liu Ting.Sentiment Analysis[J].Journal of Software,2010,1(8):1834-1848
[5] Kamps J,Marx M,Mokken R J,et al.Using WordNet to Mea-sure Semantic Orientations of Adjectives[C]∥Proc of LREC-04,4th Int Conf on Language Resources and Evaluation.Lisbon,2004:1115-1118
[6] Turney P D.Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews[C]∥Proceedings of the 40th Annual Meeting of the Association Computational Linguistics(ACL).2002:417-424
[7] Turney P D,Littman,Michael L.Measuring praise and criti-cism:inference of semantic orientation from association[J].ACM Transactions on Information Systems,2003,1(4):315-346
[8] 宋晓雷,王素格,李红霞,等.基于概率浅语义分析的词汇情感倾向判别[J].中文信息学报,2011,5(2):89-93 Song Xiao-lei,Wang Su-ge,Li Hong-xia,et al.Word Sentiment Orientation Discrimination Based on PLSA [J].Journal of Chinese Information Processing,2011,5(2):89-93
[9] Takamura H,Inui T,Okumura M.Extracting Semantic Orienta-tion of Words Using Spin Model[C]∥Proc.Ann.Meeting of the Assoc.Computational Linguistics.2005:133-140
[10] Takamura H,Inui T,Okumura M.Extracting Semantic Orientation of Phrases from Dictionary[C]∥Proc.Conf.North Am.Ch.Assoc.for Computational Linguistics.2007:292-299
[11] 杜伟夫,谭松波,云晓春,等.一种新的情感词汇语义倾向计算方法[J].计算机研究与发展,2009,6(10):1713-1720 Du Wei-fu,Tan Song-bo,Yun Xiao-chun,et al.A New Method to Compute Semantic Orientation [J].Journal of Computer Research and Development,2009,6(10):1713-1720
[12] Yoshida Y,Hirao T,Iwata T,et al.Transfer Learning for Multiple-Domain Sentiment Analysis-Identifying Domain Dependent/Independent Word Polarity[C]∥Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence.2011:1286-1291
[13] Mladenic D,Grobelnik M.Feature selection for classificationbased on text hierarchy[C]∥Proceedings of the Conference on Automated Learning and Discovery(CONALD-98).1998
[14] Bollegala D,Weir D,Carroll J.Cross-Domain Sentiment Classification Using a Sentiment Sensitive Thesaurus[J].IEEE Transactions on Knowledge and Data Engineering,2013,5(8):1719-1731
[15] Pantel P,Ravichandran D.Automatically Labeling SemanticClasses[C]∥Proc.Conf.North Am.Ch.Assoc.for Computational Linguistics:Human Language Technologies.2004:321-328
[16] Blitzer J,Dredze M,Pereira F.Biographies,bollywood,boom-boxes and blenders:Domain adaptation for sentiment classification[C]∥Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics.2007:432-439

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!