BGRU:中文文本情感分析的新方法
|
摘要
社交网络作为社会生活不可或缺的一部分,针对其产生的文本数据进行情感分析已成为自然语言处理领域的一个研究热点。鉴于深度学习技术能够自动构建文本特征,人们已提出CNN(convolutional neural network)、BLSTM(bidirectional long short-term memory)等模型来解决文本情感分析问题,但还存在结构较为复杂或训练时间较长等问题,而BGRU(bidirectional gated recurrent unit)能记忆序列的上下文信息,并且结构较为简单,训练速度较快。提出一种基于BGRU的中文文本情感分析方法,首先将文本转换为词向量序列,然后利用BGRU获得文本的上下文情感特征,最后由分类器给出文本的情感倾向。在ChnSentiCorp语料上进行实验,该方法取得了90.61%的F1值,效果优于CNN和BLSTM等模型,并且训练速度是BLSTM的1.36倍。
Social network is an indispensable part of social life, and the text sentiment analysis of social network has become a research hot topic of natural language processing. In view that deep learning technology can automatically build text features, people have proposed deep learning models such as CNN(convolutional neural network) and BLSTM(bidirectional long short-term memory) to solve text sentiment analysis, but there are still problems such as complicated structures or long training time. BGRU(bidirectional gated recurrent unit) can remember the context information of sequence, the structure is relatively simple and the training speed is fast. A Chinese text sentiment analysis method based on BGRU is proposed. This method firstly converts the text into a sequence of word vector.Then it obtains the text sentiment features through BGRU. Finally, the classifier identifies the text sentiment orientation. The experimental results on the ChnSentiCorp corpus achieve 90.61% of F1 value. It is shown that this method is superior to CNN and BLSTM, etc. And training speed is 1.36 times higher than that of BLSTM.
Social network is an indispensable part of social life, and the text sentiment analysis of social network has become a research hot topic of natural language processing. In view that deep learning technology can automatically build text features, people have proposed deep learning models such as CNN(convolutional neural network) and BLSTM(bidirectional long short-term memory) to solve text sentiment analysis, but there are still problems such as complicated structures or long training time. BGRU(bidirectional gated recurrent unit) can remember the context information of sequence, the structure is relatively simple and the training speed is fast. A Chinese text sentiment analysis method based on BGRU is proposed. This method firstly converts the text into a sequence of word vector.Then it obtains the text sentiment features through BGRU. Finally, the classifier identifies the text sentiment orientation. The experimental results on the ChnSentiCorp corpus achieve 90.61% of F1 value. It is shown that this method is superior to CNN and BLSTM, etc. And training speed is 1.36 times higher than that of BLSTM.
引文
[1]Li F T.Research on sentiment analysis with product review[D].Beijing:Tsinghua University,2011.
[2]Li R,Lin Z,Lin H L,et al.Text emotion analysis:a survey[J].Journal of Computer Research and Development,2018,55(1):30-52.
[3]Zhao Y Y,Qin B,Shi Q H,et al.Large-scale sentiment lexicon collection and its application in sentiment classification[J].Journal of Chinese Information Processing,2017,31(2):187-193.
[4]Wang C.Research on the analysis of weibo comments tendency based on machine learning methods[D].Harbin:Harbin Institute of Technology,2016.
[5]Pang B,Lee L,Vaithyanathan S.Thumbs up?:sentiment classification using machine learning techniques[C]//Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing,Pennsylvania,Jul 6-7,2002.Stroudsburg:ACL,2002:79-86.
[6]Melville P,Gryc W,Lawrence R D.Sentiment analysis of blogs by combining lexical knowledge with text classification[C]//Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,Paris,Jun 28-Jul 1,2009.New York:ACM,2009:1275-1284.
[7]Li S,Huang C R,Zhou G.Employing personal impersonal views in supervised and semisupervised sentiment classification[C]//Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics,Uppsala,Jul 11-16,2010.Stroudsburg:ACL,2010:414-423.
[8]Kumar A,Sebastian T M.Sentiment analysis on Twitter[J].International Journal of Computer Science,2012,9(4):628-633.
[9]Yao T F,Lou D C.Research on semantic orientation analysis for topics in Chinese sentences[J].Journal of Chinese Information Processing,2007,21(5):73-79.
[10]Ding X W,Liu B,Yu P S.A holistic lexicon-based approach to opinion mining[C]//Proceedings of the International Conference on Web Search and Web Data Mining,Palo Alto,Feb 11-12,2008.New York:ACM,2008:231-240.
[11]Hu M Q,Liu B.Mining and summarizing customer reviews[C]//Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,Seattle,Aug 22-25,2004.New York:ACM,2004:168-177.
[12]Zhu Y R,Min J,Zhou Y Q,et al.Semantic orientation computing based on How Net[J].Journal of Chinese Information Processing,2006,20(1):14-20.
[13]Hinton G E,Salakhutdinov R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[14]Bengio Y,Ducharme R,Vincent P,et al.A neural probabilistic language model[J].Journal of Machine Learning Research,2003,3(6):1137-1155.
[15]Mikolov T,Sutskever I,Chen K,et al.Distributed representations of words and phrases and their compositionality[C]//Proceedings of the 27th Annual Conference on Neural Information Processing Systems,Lake Tahoe,Dec 5-8,2013.Cambridge:MIT Press,2013:3111-3119.
[16]Mnih A,Hinton G E.A scalable hierarchical distributed language model[C]//Proceedings of the 22nd Annual Conference on Neural Information Processing,Vancouver,Dec8-11,2008.Red Hook:Curran Associates,2009:1081-1088.
[17]Kim Y.Convolutional neural networks for sentence classification[J].ar Xiv:1408.5882,2014.
[18]Liang J,Chai Y M,Yuan H B,et al.Polarity shifting and LSTM based recursive networks for sentiment analysis[J].Journal of Chinese Information Processing,2015,29(5):152-159.
[19]Xiao Z,Liang P J.Chinese sentiment analysis using bidirectional LSTM with word embedding[C]//LNCS 10040:Proceedings of the 2nd International Conference on Cloud Computing and Security,Nanjing,Jul 29-31,2016.Berlin,Heidelberg:Springer,2016:601-610.
[20]Liu L F,Yang L,Zhang S W,et al.Convolution neural networks for Chinese micro-blog sentiment analysis[J].Journal of Chinese Information Processing,2015,29(6):159-165.
[21]Feng X J,Zhang Z W,Shi J C.Text sentiment analysis based on convolutional neural networks and attention model[J].Application Research of Computers,2018,35(5):1434-1436.
[22]Liang B,Liu Q,Xu J,et al.Aspect-based sentiment analysis based on multi-attention CNN[J].Journal of Computer Research and Development,2017,54(8):1724-1735.
[23]Du H,Xu X K,Wu D Y,et al.A sentiment classification method based on sentiment-specific word embedding[J].Journal of Chinese Information Processing,2017,31(3):170-176.
[24]Cleeremans A,Servan-Schreiber D,Mcclelland J L.Finite state automata and simple recurrent networks[J].Neural Computation,1989,1(3):372-381.
[25]Hochreiter S,Schmidhuber J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[26]Cho K,Merrienboer B V,Gül?ehre?,et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing,Doha,Oct 25-29,2014.Stroudsburg:ACL,2014:1724-1735.
[27]Schuster M,Paliwal K K.Bidirectional recurrent neural networks[J].IEEE Transactions on Signal Processing,1997,45(11):2673-2681.
[1]李方涛.基于产品评论的情感分析研究[D].北京:清华大学,2011.
[2]李然,林政,林海伦,等.文本情绪分析综述[J].计算机研究与发展,2018,55(1):30-52.
[3]赵妍妍,秦兵,石秋慧,等.大规模情感词典的构建及其在情感分类中的应用[J].中文信息学报,2017,31(2):187-193.
[4]汪淳.基于机器学习的微博评论信息倾向性分析的研究[D].哈尔滨:哈尔滨工业大学,2016.
[9]姚天昉,娄德成.汉语语句主题语义倾向性分析方法的研究[J].中文信息学报,2007,21(5):73-79.
[12]朱嫣然,闵锦,周雅倩,等.基于How Net的词汇语义倾向计算[J].中文信息学报,2006,20(1):14-20.
[18]梁军,柴玉梅,原慧斌,等.基于极性转移和LSTM递归网络的情感分析[J].中文信息学报,2015,29(5):152-159.
[20]刘龙飞,杨亮,张邵武,等.基于卷积神经网络的微博情感倾向性分析[J].中文信息学报,2015,29(6):159-165.
[21]冯兴杰,张志伟,史金钏.基于卷积神经网络和注意力模型的文本情感分析[J].计算机应用研究,2018,35(5):1434-1436.
[22]梁斌,刘全,徐进,等.基于多注意力卷积神经网络的特定目标情感分析[J].计算机研究与发展,2017,54(8):1724-1735.
[23]杜慧,徐学可,伍大勇,等.基于情感词向量的微博情感分类[J].中文信息学报,2017,31(3):170-176.
[2]Li R,Lin Z,Lin H L,et al.Text emotion analysis:a survey[J].Journal of Computer Research and Development,2018,55(1):30-52.
[3]Zhao Y Y,Qin B,Shi Q H,et al.Large-scale sentiment lexicon collection and its application in sentiment classification[J].Journal of Chinese Information Processing,2017,31(2):187-193.
[4]Wang C.Research on the analysis of weibo comments tendency based on machine learning methods[D].Harbin:Harbin Institute of Technology,2016.
[5]Pang B,Lee L,Vaithyanathan S.Thumbs up?:sentiment classification using machine learning techniques[C]//Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing,Pennsylvania,Jul 6-7,2002.Stroudsburg:ACL,2002:79-86.
[6]Melville P,Gryc W,Lawrence R D.Sentiment analysis of blogs by combining lexical knowledge with text classification[C]//Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,Paris,Jun 28-Jul 1,2009.New York:ACM,2009:1275-1284.
[7]Li S,Huang C R,Zhou G.Employing personal impersonal views in supervised and semisupervised sentiment classification[C]//Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics,Uppsala,Jul 11-16,2010.Stroudsburg:ACL,2010:414-423.
[8]Kumar A,Sebastian T M.Sentiment analysis on Twitter[J].International Journal of Computer Science,2012,9(4):628-633.
[9]Yao T F,Lou D C.Research on semantic orientation analysis for topics in Chinese sentences[J].Journal of Chinese Information Processing,2007,21(5):73-79.
[10]Ding X W,Liu B,Yu P S.A holistic lexicon-based approach to opinion mining[C]//Proceedings of the International Conference on Web Search and Web Data Mining,Palo Alto,Feb 11-12,2008.New York:ACM,2008:231-240.
[11]Hu M Q,Liu B.Mining and summarizing customer reviews[C]//Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,Seattle,Aug 22-25,2004.New York:ACM,2004:168-177.
[12]Zhu Y R,Min J,Zhou Y Q,et al.Semantic orientation computing based on How Net[J].Journal of Chinese Information Processing,2006,20(1):14-20.
[13]Hinton G E,Salakhutdinov R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[14]Bengio Y,Ducharme R,Vincent P,et al.A neural probabilistic language model[J].Journal of Machine Learning Research,2003,3(6):1137-1155.
[15]Mikolov T,Sutskever I,Chen K,et al.Distributed representations of words and phrases and their compositionality[C]//Proceedings of the 27th Annual Conference on Neural Information Processing Systems,Lake Tahoe,Dec 5-8,2013.Cambridge:MIT Press,2013:3111-3119.
[16]Mnih A,Hinton G E.A scalable hierarchical distributed language model[C]//Proceedings of the 22nd Annual Conference on Neural Information Processing,Vancouver,Dec8-11,2008.Red Hook:Curran Associates,2009:1081-1088.
[17]Kim Y.Convolutional neural networks for sentence classification[J].ar Xiv:1408.5882,2014.
[18]Liang J,Chai Y M,Yuan H B,et al.Polarity shifting and LSTM based recursive networks for sentiment analysis[J].Journal of Chinese Information Processing,2015,29(5):152-159.
[19]Xiao Z,Liang P J.Chinese sentiment analysis using bidirectional LSTM with word embedding[C]//LNCS 10040:Proceedings of the 2nd International Conference on Cloud Computing and Security,Nanjing,Jul 29-31,2016.Berlin,Heidelberg:Springer,2016:601-610.
[20]Liu L F,Yang L,Zhang S W,et al.Convolution neural networks for Chinese micro-blog sentiment analysis[J].Journal of Chinese Information Processing,2015,29(6):159-165.
[21]Feng X J,Zhang Z W,Shi J C.Text sentiment analysis based on convolutional neural networks and attention model[J].Application Research of Computers,2018,35(5):1434-1436.
[22]Liang B,Liu Q,Xu J,et al.Aspect-based sentiment analysis based on multi-attention CNN[J].Journal of Computer Research and Development,2017,54(8):1724-1735.
[23]Du H,Xu X K,Wu D Y,et al.A sentiment classification method based on sentiment-specific word embedding[J].Journal of Chinese Information Processing,2017,31(3):170-176.
[24]Cleeremans A,Servan-Schreiber D,Mcclelland J L.Finite state automata and simple recurrent networks[J].Neural Computation,1989,1(3):372-381.
[25]Hochreiter S,Schmidhuber J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[26]Cho K,Merrienboer B V,Gül?ehre?,et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing,Doha,Oct 25-29,2014.Stroudsburg:ACL,2014:1724-1735.
[27]Schuster M,Paliwal K K.Bidirectional recurrent neural networks[J].IEEE Transactions on Signal Processing,1997,45(11):2673-2681.
[1]李方涛.基于产品评论的情感分析研究[D].北京:清华大学,2011.
[2]李然,林政,林海伦,等.文本情绪分析综述[J].计算机研究与发展,2018,55(1):30-52.
[3]赵妍妍,秦兵,石秋慧,等.大规模情感词典的构建及其在情感分类中的应用[J].中文信息学报,2017,31(2):187-193.
[4]汪淳.基于机器学习的微博评论信息倾向性分析的研究[D].哈尔滨:哈尔滨工业大学,2016.
[9]姚天昉,娄德成.汉语语句主题语义倾向性分析方法的研究[J].中文信息学报,2007,21(5):73-79.
[12]朱嫣然,闵锦,周雅倩,等.基于How Net的词汇语义倾向计算[J].中文信息学报,2006,20(1):14-20.
[18]梁军,柴玉梅,原慧斌,等.基于极性转移和LSTM递归网络的情感分析[J].中文信息学报,2015,29(5):152-159.
[20]刘龙飞,杨亮,张邵武,等.基于卷积神经网络的微博情感倾向性分析[J].中文信息学报,2015,29(6):159-165.
[21]冯兴杰,张志伟,史金钏.基于卷积神经网络和注意力模型的文本情感分析[J].计算机应用研究,2018,35(5):1434-1436.
[22]梁斌,刘全,徐进,等.基于多注意力卷积神经网络的特定目标情感分析[J].计算机研究与发展,2017,54(8):1724-1735.
[23]杜慧,徐学可,伍大勇,等.基于情感词向量的微博情感分类[J].中文信息学报,2017,31(3):170-176.