Emotion Analysis Model Using Compositional Semantics
-
摘要: 文本情绪分析属于细颗粒度文本情感分析范畴.传统的基于 监督学习的方法,大多注重从表面词形提取特征,对语言的结构化特征 考虑较少,无法应对特征稀疏问题,也无法挖掘文本中隐含的深层语 言信息(包括词语搭配和语义韵).上述问题的存在导致现有系统 的分类性能不高,尤其对隐性文本情绪分类问题表现出较大的局限 性.本文尝试将基于依存句法的词语搭配特征和基于组合语义的深度 特征应用于文本情绪分类,提出了一种以短语为主要线索的半马 尔科夫条件随机场文本情绪分析模型.为了验证模型的有效性,利 用实际构建的相关实验语料,开展了相关实验研究.实验结果表 明,本文方法不仅可以显著提高文本情绪分类的准确率,而且对解 决隐性情感分析问题也具有重要作用.
-
关键词:
- 文本情绪分析 /
- 隐性情绪分类 /
- 组合语义 /
- 半 马尔科夫条件随机场
Abstract: Emotion analysis is one of the challenging tasks in the fine-grained sentiment analysis field. Conventional supervised learning approaches reply on features based on surface word forms and neglect linguistic structure of text. Hence, they usually suffer from sparse features and are unable to exploit implicit information such as collocation and semantic prosody, leading to unsatisfactory performance, especially for identifying implicit emotion expression. This paper first explores dependency parsing features and compositional semantics information in emotion. Then it proposes a phrase level emotion detection model based on semi-CRFs (semi-Markov conditional random fields) and finally creates several corpora and carries out corresponding experiment. The experimental results indicate that the model and features are remarkably effective to classify sentence or short text by fine-grained emotion tags and play an important role in implicit emotion detection. -
[1] Lutz C, White G M. The anthropology of emotions. Annual Review of Anthropology, 1986, 15: 405-436 [2] Wei Nai-Xing. Fundamentals of Lexis. Shanghai: Shanghai Foreign Language Education Press, 2011.(卫乃兴. 词语学要义. 上海: 上海外语教育出版社, 2011.) [3] Alm C O, Roth D, Sproat R. Emotions from text: machine learning for text-based emotion prediction. In: Proceedings of the 2005 Conference on Human Language Technology and Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2005. 579-586 [4] Aman S, Szpakowicz S. Using roget's thesaurus for fine-grained emotion recognition. In: Proceedings of the 3rd International Joint Conference on Natural Language Processing. Hyderabad, India: Researchgate, 2008. 312-318 [5] Das D, Bandyopadhyay S. Word to sentence level emotion tagging for Bengali blogs. In: Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the AFNLP. Stroudsburg, PA, USA: Association for Computational Linguistics, 2009. 149-152 [6] Nakagawa T, Inui K, Kurohashi S. Dependency tree-based sentiment classification using CRFs with hidden variables. In: Proceedings of Human Language Technologies: the 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics, 2010. 786-794 [7] Xu Bing, Zhao Tie-Jun, Wang Shan-Yu, Zheng De-Quan. Extraction of opinion targets based on shallow parsing features. Acta Automatica Sinica, 2011, 37(10): 1241-1247(徐冰, 赵铁军, 王山雨, 郑德权. 基于浅层句法特征的评价对象抽取研究. 自动化学报, 2011, 37(10): 1241-1247) [8] Neviarouskaya A, Prendinger H, Ishizuka M. Compositionality principle in recognition of fine-grained emotions from text. In: Proceedings of International Conference on Weblogs and Social Media. San Jose, California: The AAAI Press, 2009. 6-24 [9] Neviarouskaya A, Prendinger H, Ishizuka M. Recognition of affect, judgment, and appreciation in text. In: Proceedings of the 23rd International Conference on Computational Linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics, 2010. 806-814 [10] Chaffar S, Inkpen D. Using a heterogeneous dataset for emotion analysis in text. In: Proceedings of the Canadian AI'11 Proceedings of the 24th Canadian conference on Advances in Artificial Intelligence. St. John's, Canada: Springer, 2011. 62-67 [11] Mohammad S, Turney P D. Emotions evoked by common words and phrases: using mechanical Turk to create an emotion lexicon. In: Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text. Stroudsburg, PA, USA: Association for Computational Linguistics, 2010. 26-34 [12] Volkova S, Dolan W B, Wilson T. CLex: a lexicon for exploring color, concept and emotion associations in language. In: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics, 2012. 306-314 [13] Purver M, Battersby S. Experimenting with distant supervision for emotion classification. In: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics, 2012. 482-491 [14] Qadir A, Riloff E. Bootstrapped learning of emotion hashtags #hashtags4you. In: Proceeding of the 4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. Stroudsburg, PA, USA: Association for Computational Linguistics, 2013. 2-11 [15] Quan C Q, Ren F J. Construction of a blog emotion corpus for Chinese emotional expression analysis. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2009. 1446-1454 [16] Xu G, Meng X F, Wang H F. Build Chinese emotion lexicons using a graph-based algorithm and multiple resources. In: Proceedings of the 23rd International Conference on Computational Linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics, 2010. 1209-1217 [17] Wang L, Yu S W. Construction of a Chinese idiom knowledge base and its applications. In: Proceedings of the Multiword Expressions: From Theory to Applications (MWE 2010). Beijing, China: Association for Computational Linguistics, 2010. 11-18 [18] Yang M, Peng B L, Chen Z, Zhu D J, Chow K P. A topic model for building fine-grained domain-specific emotion lexicon. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics, 2014. 421-426 [19] Choi Y, Cardie C. Learning with compositional semantics as structural inference for subsentential sentiment analysis. In: Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2008. 793-801 [20] Mitchell J, Lapata M. Vector-based models of semantic composition. In: Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics, 2008. 236-244 [21] Baroni M, Zamparelli R. Nouns are vectors, adjectives are matrices: representing adjective-noun constructions in semantic space. In: Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2010. 1183-1193 [22] Socher R, Pennington J, Huang E H, Ng A Y, Manning C D. Semi-supervised recursive autoencoders for predicting sentiment distributions. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2011. 151-161 [23] Socher R, Huval B, Manning C D, Ng A Y. Semantic compositionality through recursive matrix-vector spaces. In: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Stroudsburg, PA, USA: Association for Computational Linguistics, 2012. 1201-1211 [24] Moilanen K, Pulman S. Sentiment composition. In: Proceedings of Recent Advances in Natural Language Processing. Borovets, Bulgaria: University of Oxford, 2007. 378-382 [25] Yessenalina A, Cardie C. Compositional matrix-space models for sentiment analysis. In: Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2011. 172-182 [26] Mohammad S. Portable features for classifying emotional text. In: Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, PA, USA: Association for Computational Linguistics, 2012. 587-591 [27] Hermann K M, Blunsom P. The role of syntax in vector space models of compositional semantics. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics, 2013. 894-904 [28] Sui Zhi-Fang, Yu Shi-Wen. The research on recognizing the predicate head of a Chinese simple sentence in EBMT. Journal of Chinese Information Processing, 1998, 12(4): 39-46(穗志方, 俞士汶. 面向EBMT的汉语单句谓语中心词识别研究. 中文信息学报, 1998, 12(4): 39-46) [29] Turian J, Ratinov L, Bengio Y. Word representations: a simple and general method for semi-supervised learning. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA, USA: Association for Computational Linguistics, 2010. 384-394 [30] Sarawagi S, Cohen W W. Semi-Markov conditional random fields for information extraction. In: Proceedings of the Eighteenth Annual Conference on Neural Information Processing Systems. Montreal, Quebec, Canada, 2004.
点击查看大图
计量
- 文章访问数: 1924
- HTML全文浏览量: 102
- PDF下载量: 1490
- 被引次数: 0