[1]李松如,陈锻生.采用循环神经网络的情感分析注意力模型[J].华侨大学学报(自然科学版),2018,39(2):252-255.[doi:10.11830/ISSN.1000-5013.201606123]
　LI Songru,CHEN Duansheng.Recurrent Neural Network Using Attention Model for Sentiment Analysis[J].Journal of Huaqiao University(Natural Science),2018,39(2):252-255.[doi:10.11830/ISSN.1000-5013.201606123]
点击复制

采用循环神经网络的情感分析注意力模型()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第39卷
期数:
2018年第2期
页码:
252-255
栏目:
出版日期:
2018-03-20

文章信息/Info

Title:
Recurrent Neural Network Using Attention Model for Sentiment Analysis
文章编号:
1000-5013(2018)02-0252-04
作者:
李松如;  陈锻生
华侨大学 计算机科学与技术学院, 福建 厦门 361021
Author(s):
LI Songru;  CHEN Duansheng
College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China
关键词:
情感分析;  循环神经网络;  注意力;  长短时记忆
Keywords:
sentiment analysis;  recurrent neural network;  attention;  long short term memory
分类号:
TP311
DOI:
10.11830/ISSN.1000-5013.201606123
文献标志码:
A
摘要:
针对目前情感分析中的循环神经网络模型缺乏对情感词的关注的问题,提出一种基于循环神经网络的情感词注意力模型,通过引入注意力机制,在情感分类时着重考虑文本中的情感词的影响.在NLPCC 2014情感分析数据集及IMDB影评数据集上进行试验,结果表明:该模型能够提高情感分析的效果.
Abstract:
Aim at the overlook of emotional words in the present recurrent neural network model used for sentiment analysis, we propose an emotional word attention model based on recurrent neural network. By introducing the attention mechanism, the model can pay more attention to the emotional words in the text sentiment classification. Experiments are conducted on the NLPCC 2014 sentiment analysis dataset and IMDB movie review dataset, the results show that our model can improve the sentiment analysis effect.

参考文献/References:

[1] LIU Bing.Sentiment analysis and opinion mining[J].Synthesis Lectures on Human Language Technologies,2012,5(1):1-167.
[2] 赵妍妍,秦兵,刘挺.文本情感分析[J].软件学报,2010,21(8):1834-1848.DOI:10.3724/SP.J.1001.2010.03832.
[3] PANG Bo,LEE L,VAITHYANATHAN S.Thumbs up?Sentiment classification using machine learning techniques[C]//Proceedings of Conference on Empirical Methods in Natural Language Processing.Philadelphia:[s.n.],2002:79-86.
[4] MIKOLOV T,SUTSKEVER I,CHEN Kai,et al.Distributed representations of words and phrases and their compositionality[J].Advances in Neural Information Processing Systems,2013,26:3111-3119.
[5] KIM Y.Convolutional neural networks for sentence classification[C]//Conference on Empirical Methods in Natural Language Processing.Doha:[s.n.],2014:1746-1751.DOI:10.3115/v1/D14-1181.
[6] IRSOY O,CARDIE C.Opinion mining with deep recurrent neural networks[C]//Conference on Empirical Methods in Natural Language Processing.Doha:[s.n.],2014:720-728.DOI:10.3115/v1/D14-1080.
[7] BAHDANAU D,CHO K,BENGIO Y.Neural machine translation by jointly learning to align and translate[EB/OL].(2015-04-24)[2016-05-12] .https://arxiv.org/pdf/1409.0473v6.
[8] RUSH A M,CHOPRA S,WESTON J.A neural attention model for abstractive sentence summarization[C]//Conference on Empirical Methods in Natural Language Processing.Lisbon:[s.n.],2015:379-389.DOI:10.18653/v1/D15-1044.
[9] XU K,BA J,KIROS R,et al.Show, attend and tell: Neural image caption generation with visual attention[C]//Proceedings of the 32nd International Conference on Machine Learning.Lille:ACM,2015:2048-2057.
[10] GRAVES A.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[11] SCHUSTER M,PALIWAL K K.Bidirectional recurrent neural networks[J].IEEE Transactions on Signal Processing,1997,45(11):2673-2681.DOI:10.1109/78.650093.
[12] MESNIL G,MIKOLOV T,RANZATO M A,et al.Ensemble of generative and discriminative techniques for sentiment analysis of movie reviews[J].Journal of Lightwave Technology,2014,32(17):3043-3060.
[13] ZEILER M D.ADADELTA: An adaptive learning rate method[EB/OL].(2012-12-22)[2016-05-12] .http://arxiv.org/pdf/1212.5701v1.pdf.

相似文献/References:

[1]吴琼,陈锻生.多尺度卷积循环神经网络的情感分类技术[J].华侨大学学报(自然科学版),2017,38(6):875.[doi:10.11830/ISSN.1000-5013.201606077]
　WU Qiong,CHEN Duansheng.Sentiment Classification With Multiscale Convolutional Recurrent Neural Network[J].Journal of Huaqiao University(Natural Science),2017,38(2):875.[doi:10.11830/ISSN.1000-5013.201606077]

备注/Memo

备注/Memo:
收稿日期: 2016-07-01
通信作者: 陈锻生(1959-),男,教授,博士,主要从事计算机视觉与多媒体技术的研究.E-mail:dschen@hqu.edu.cn.
基金项目: 国家自然科学基金资助项目(61370006); 福建省科技计划(工业引导性)重点项目(2015H0025)
更新日期/Last Update: 2018-03-20