中文微博情感分析旨在发现用户对热点事件的观点态度。已有的研究大多使用SVM、CRF等传统算法根据手工标注情感特征对微博情感进行分析。该文主要探讨利用深度学习来做中文微博情感分析的可行性,采用递归神经网络来发现与任务相关的特征,避免依赖于具体任务的人工特征设计,并根据句子词语间前后的关联性引入情感极性转移模型加强对文本关联性的捕获。该文提出的方法在性能上与当前采用手工标注情感特征的方法相当,但节省了大量人工标注的工作量。
Abstract
Chinese micro-blog sentiment analysis aims to discover the user attitude towards hot events. Most of the current studies analyze the micro-blog sentiment by traditional algorithms such as SVM, CRF based on hand-engineered features. This paper explores the feasibility of performing Chinese micro-blog sentiment analysis by deep learning. We try to avoid task-specific features, and use recursive neural networks to discover relevant features to the tasks. We propose a novel model - sentiment polarity transition model - based on the relationship between neighboring words of a sentence to strengthen the text association. The proposed method achieves a performance close to state-of-the-art methods based on the hand-engineered features, but saving a lot of manual annotation work.
关键词
深度学习 /
微博情感分析 /
递归神经网络 /
自编码
{{custom_keyword}} /
Key words
deep learning /
micro-blog sentiment analysis /
recursive neural networks /
autoencoder
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] B. Pang, L. Lee. Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales[C]Proceedings of the ACL, 2005: 115-124.
[2] 唐慧丰,谭松波,程学旗.基于监督学习的中文情感分类技术比较研究[J].中文信息学报 2007, 6(2):88-94
[3] Y. Bengio, R. Ducharme, P. Vincent, et al. A neural probabilistic language model[J]. Journal of Machine Learning Research, 2003,3:1137-1155.
[4] Collobert R, Weston J. A unified architecture for natural language processing: Deep neural networks with multitask learning[C]//Proceedings of the 25th international conference on Machine learning. ACM, 2008: 160-167.
[5] Mnih A, Hinton G E. A Scalable Hierarchical Distributed Language Model[C]//Proceedings of NIPS. 2008: 1081-1088.
[6] Mikolov T, Karafiát M, Burget L, et al. Recurrent neural network based language model[C]//Proceedings of INTERSPEECH. 2010: 1045-1048.
[7] Mikolov T, Kombrink S, Burget L, et al. Extensions of recurrent neural network language model[C]//Proceedings of Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on. IEEE, 2011: 5528-5531.
[8] Kombrink S, Mikolov T, Karafiát M, et al. Recurrent Neural Network Based Language Modeling in Meeting Recognition[C]//Proceedings of INTERSPEECH. 2011: 2877-2880.
[9] Mikolov T, Chen K, Corrado G, et al. Efficient estimation of word representations in vector space[J]. arXiv preprint arXiv:1301.3781, 2013.
[10] Richard Socher, Jeffrey Pennington, Eric Huang, et al. Manning Conference onEmpirical Methods in Natural Language Processing (EMNLP 2011, Oral ) Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions.2011.
[11] 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. Association for Computational Linguistics, 2002: 417-424.
[12] Kennedy A, Inkpen D. Sentiment classification of movie reviews using contextual valence shifters[J]. Computational Intelligence, 2006, 22(2): 110-125.
[13] 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.
[14] Lin C, He Y, Everson R. A comparative study of Bayesian models for unsupervised sentiment detection[C]//Proceedings of the Fourteenth Conference on Computational Natural Language Learning. Association for computational linguistics, 2010: 144-152.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(60970083,61272221)、国家社会科学基金(14BYY096)、国家高技术研究发展863计划(2012AA011101)、河南省科技厅科技攻关计划项目(132102210407),河南省科技厅基础研究项目(142300410231,142300410308)、河南省教育厅科学技术研究重点项目(12B520055,13B520381)。
{{custom_fund}}
PDF(2605 KB)
