基于对比散度受限玻尔兹曼机深度学习的产品评论情感分析

doi:10.11772/j.issn.1001-9081.2016.04.1045

计算机应用 ›› 2016, Vol. 36 ›› Issue (4): 1045-1049.DOI: 10.11772/j.issn.1001-9081.2016.04.1045

基于对比散度受限玻尔兹曼机深度学习的产品评论情感分析

高琰¹, 陈白帆¹, 晁绪耀¹, 毛芳²

1. 中南大学信息科学与工程学院, 长沙 410083;
2. 中南大学软件学院, 长沙 410083

收稿日期:2015-09-25 修回日期:2015-12-09 出版日期:2016-04-10 发布日期:2016-04-08
通讯作者: 陈白帆
作者简介:高琰(1973-),女,江苏宜兴人,副教授,博士,主要研究方向:智能信息处理、Web智能、数据挖掘; 陈白帆(1979-),女,湖南常德人,讲师,博士,主要研究方向:人工智能、机器学习; 晁绪耀(1991-),女,河南南阳人,硕士,主要研究方向:智能信息处理; 毛芳(1991-),女,湖南衡阳人,硕士研究生,主要研究方向:智能信息处理、模式识别。
基金资助:
国家自然科学基金资助项目(61403423);湖南省科技计划项目(2014FJ3157);自主系统与网络控制教育部重点实验室开放基金资助项目(2013A11)。

Sentiment analysis of product reviews based on contrastive divergence- restricted Boltzmann machine deep learning

GAO Yan¹, CHEN Baifan¹, CHAO Xuyao¹, MAO Fang²

1. School of Information Science and Engineering, Central South University, Changsha Hunan 410083, China;
2. School of Software, Central South University, Changsha Hunan 410083, China

Received:2015-09-25 Revised:2015-12-09 Online:2016-04-10 Published:2016-04-08
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61403423), the Science and Technology Planning Project of Hunan Province (2014FJ3157), the Foundation of Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education (2013A11).

摘要/Abstract

摘要： 针对目前大部分情感分析技术需要人工标注建立情感词典提取情感特征的问题,提出一种基于对比散度-受限玻尔兹曼机(CD-RBM)深度学习的产品评论情感分析方法。该方法在对产品评论时进行数据预处理并利用词袋模型产生产品评论的向量表示,然后通过CD-RBM提取产品评论的情感特征,最后结合支持向量机(SVM)将提取出来的情感特征进行文本情感分类。CD-RBM无需人工标注情感词典,即可获得情感特征,且可以提高特征的情感语义关联性;同时,SVM可以保证产品评论情感分类的准确度。通过实验确定了RBM最优训练周期为10,在此训练周期下对RBM、SVM、PCA+SVM,以及RBM+SVM方法进行了比较。实验结果表明,RBM特征提取和SVM分类结合方法能够获得最好的准确率和F值,并获得较好的召回率。

关键词: 深度学习, 受限玻尔兹曼机, 情感分析, 对比散度, 支持向量机

Abstract: Focusing on the issue that most of existing approaches need sentiment lexicon annotated manually to extract sentiment features, a sentiment analysis method of product reviews based on Contrastive Divergence-Restricted Boltzmann Machine (CD-RBM) deep learning was proposed. Firstly, product reviews were preprocessed and represented as vectors using the bag-of-words. Secondly, CD-RBM was used to extract the sentiment features from product review vectors. Finally, the sentiment features were classified with Support Vector Machine (SVM) as the sentiment analysis result. Without any manually pre-defined sentiment lexicon, CD-RBM can automatically obtain the sentiment features of higher semantic relevance; combining with SVM, the correctness of the sentiment analysis result is guaranteed. The optimum training period of RBM was experimentally determined as 10. In the comparison experiments with methods including RBM, SVM, PCA+SVM and RBM+SVM, the combination method of CD-RBM feature extraction and SVM classification shows the best precision and best F-measure, as well as better recall.

Key words: deep learning, Restricted Boltzmann Machine (RBM), sentiment analysis, contrastive divergence, Support Vector Machine (SVM)

中图分类号:

TP391.4

高琰, 陈白帆, 晁绪耀, 毛芳. 基于对比散度受限玻尔兹曼机深度学习的产品评论情感分析[J]. 计算机应用, 2016, 36(4): 1045-1049.

GAO Yan, CHEN Baifan, CHAO Xuyao, MAO Fang. Sentiment analysis of product reviews based on contrastive divergence- restricted Boltzmann machine deep learning[J]. Journal of Computer Applications, 2016, 36(4): 1045-1049.

参考文献

[1] 任远远, 王卫平. 中文网络评论的产品特征提取及情感倾向判定. 计算机系统应用, 2014, 23(11):22-27.(REN Y Y, WANG W P. Extracting product features and determine sentiment orientation from Chinese online reviews[J]. Computer Systems & Applications, 2014, 23(11):22-27.)
[2] 张春霞, 姬楠楠, 王冠伟. 受限波尔兹曼机简介[EB/OL].[2015-02-10]. http://www.paper.edu.cn/releasepaper/content/201301-528.(ZHANG C X, JI N N, WANG G W. Introduction of restricted Boltzmann machines[EB/OL].[2015-02-10]. http://www.paper.edu.cn/releasepaper/content/201301-528.)
[3] 王文华, 朱艳辉, 徐叶强, 等. 基于SVM的产品评论属性特征的情感倾向分析[J]. 湖南工业大学大学学报, 2012, 26(5):76-80.(WANG W H, ZHU Y H, XU Y Q, et al. Analysis on emotional tendences of attribute characteristics in product reviews based on SVM[J]. Journal of Hunan University of Technology, 2012, 26(5):76-80.)
[4] 杨立公, 汤世平, 朱俭, 等. 基于马尔科夫逻辑网的句子情感分析方法[J]. 北京理工大学学报, 2013, 33(6):600-604.(YANG L G, TANG S P, ZHU J, et al. A Markov logic network based sentence sentimental analysis method[J]. Transactions of Beijing Institute of Technology, 2013, 33(6):600-604.)
[5] RUSLAN S, ANDRIY M, GEOFFREY H. Restricted Boltzmann machines for collaborative filtering[C]//Proceedings of the 24th International Conference on Machine Learning. New York:ACM, 2007:791-798.
[6] GLOROT X, BORDES A, BENGIO Y. Domain adaptation for large-scale sentiment classification:a deep learning approach[EB/OL].[2015-02-10]. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.231.3442.
[7] 姚娜娜. 基于机器学习的产品评论情感分类研究[D]. 北京:首都师范大学, 2013:41-46.(YAO N N. Research on sentimental classification of product reviews based on machine learning[D]. Beijing:Capital Normal University, 2013:41-46.)
[8] PANG B, LEE L, VAITHYANATHAN S. Thumbs up? Sentiment classification using machine learning techniques[C]//EMNLP 2002:Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA:Association for Computational Linguistics, 2002, 10:79-86.
[9] DAVE K, LAWRENCE S, PENNOCK D. Mining the peanut gallery:opinion extraction and semantic classification of product reviews[C]//WWW 2003:Proceedings of the 12th International Word Wide Web Conference. New York:ACM, 2003:519-528.
[10] KIM S M, HOVY E. Determining the sentiment of opinions[C]//COLING 2004:Proceedings of the 20th International Conference on Computational Linguistics. Stroudsburg, PA, USA:Association for Computational Linguistics, 2004:Article No. 1367.
[11] COLLOBERT R, WESTON J. A unified architecture for natural language processing deep neural networks with multitask learning[C]//ICML 2008:Proceedings of the 25th International Conference on Machine Learning. New York:ACM, 2008:160-167.
[12] LAUZON F Q. An introduction to deep learning[C]//Proceedings of the 2012 11th International Conference on Information Science, Signal Processing and Their Applications. Piscataway, NJ:IEEE, 2012:1438-1439.
[13] YOUNES L. On the convergence of Markovian stochastic algorithms with rapidly decreasing ergodicity rates[J]. Stochastics:An International Journal of Probability and Stochastic Processes, 1999, 65(3/4):177-228.
[14] CARREIA-PERPINAN M A, HINTON G E. On contrastive divergence learning[EB/OL].[2015-02-10]. http://www.gatsby.ucl.ac.uk/aistats/fullpapers/217.pdf.
[15] HAN J W, MICHELING K, JIAN P. 数据挖掘概念与技术[M].3版.北京:机械工业出版社, 2012:315-317.(HAN J W, MICHELING K, JIAN P. Data Mining:Concept and Techniques[M]. 3rd ed. Beijing:China Machine Press, 2012:315-317.)
[16] 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, 21(6):87-94.(TANG H F, TAN S B, CHENG X Q. Research on sentiment classification of chinese reviews based on supervised machine learning techniques[J]. Journal of Chinese Information Processing, 2007, 21(6):87-94.)

基于对比散度受限玻尔兹曼机深度学习的产品评论情感分析

Sentiment analysis of product reviews based on contrastive divergence- restricted Boltzmann machine deep learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[2]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[3]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[4]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[5]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[6]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[7]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.
[8]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[9]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[10]	王月, 江逸茗, 兰巨龙. 基于改进三元组网络和K近邻算法的入侵检测[J]. 计算机应用, 2021, 41(7): 1996-2002.
[11]	李亚芳, 梁烨, 冯韦玮, 祖宝开, 康玉健. 基于社区优化的深度网络嵌入方法[J]. 计算机应用, 2021, 41(7): 1956-1963.
[12]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[13]	杜炎, 吕良福, 焦一辰. 基于模糊推理的模糊原型网络[J]. 计算机应用, 2021, 41(7): 1885-1890.
[14]	侯笑晗, 金国栋, 谭力宁, 薛远亮. 基于自适应和最优特征的合成孔径雷达舰船检测方法[J]. 计算机应用, 2021, 41(7): 2150-2155.
[15]	黄梨, 卢龙. 基于长距离依赖编码与深度残差U-Net的缺血性卒中病灶分割[J]. 计算机应用, 2021, 41(6): 1820-1827.