Please wait a minute...
Advanced Search
数据分析与知识发现  2019, Vol. 3 Issue (4): 71-79     https://doi.org/10.11925/infotech.2096-3467.2018.0516
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于深度信念网络的文本情感分类研究*
张庆庆1(),贺兴时2,王慧敏2,蒙胜军3
1西安工程大学管理学院 西安 710048
2西安工程大学理学院 西安 710048
3西安交通大学新闻与新媒体学院 西安 710049
Text Sentiment Classification Based on Deep Belief Network
Qingqing Zhang1(),Xingshi He2,Huimin Wang2,Shengjun Meng3
1School of Management, Xi’an Polytechnic University, Xi’an 710048, China
2School of Science, Xi’an Polytechnic University, Xi’an 710048, China
3School of Journalism and New Media, Xi’an Jiaotong University, Xi’an 710049, China
全文: PDF (1516 KB)   HTML ( 3
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】将深度信念网络应用于中文文本情感分类, 系统研究深度信念网络在文本情感分类任务中的参数选择与性能分析。【方法】以中文电子商务网站评论数据为研究对象, 提取一元词、二元词、词性、简单依存关系、情感得分和三元组依存关系特征作为深度信念网络的输入, 通过设置不同网络深度、不同输入维数的网络结构计算分类准确率。【结果】实验结果表明, 三元组依存关系特征作为深度信念网络的输入分类效果更好, 而网络层数对分类准确率的影响不大。【局限】尚未在其他深度学习模型上进行实验验证。【结论】深度学习在文本情感分类任务中性能良好, 验证了深度学习对复杂任务有很强的学习能力, 但其模型选择和参数设置尚需要进一步的研究。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
张庆庆
贺兴时
王慧敏
蒙胜军
关键词 深度信念网络文本情感分类参数选择    
Abstract

[Objective] This paper focused on Chinese text sentiment classification based on deep belief network, especially the parameter selection and performance analysis of the network. [Methods] Chinese e-commercial reviews are as the object of the study, the unigram, bigram, POS, simple dependency label, sentiment score and triple dependency features are extracted and used as the input of deep belief network by setting different layers and different input numbers to compute the accuracy of sentiment classification. [Results] The results demonstrate that the triple dependency features as the input got better classification performance than the other features, but the number of hidden layers doesn’t have an effect on the classification accuracy. [Limitations] The methods aren’t conducted and verified on other deep learning models. [Conclusions] Deep learning has a good performance for sentiment analysis, but how to set up parameters still need to be further considered.

Key wordsDeep Belief Network    Text Sentiment Classification    Parameter Selection
收稿日期: 2018-05-08      出版日期: 2019-05-29
基金资助:*本文系教育部人文社会科学青年基金项目“社会媒体网络社群对城市弱势群体公共事务参与的影响研究”(项目编号: 18YJC860025)、西安工程大学博士科研启动金“基于深度学习的中文文本情感分类研究”(项目编号: 107020309)和2019年陕西省教育厅科研计划专项项目“基于深度学习的情感分类研究”的研究成果之一
引用本文:   
张庆庆,贺兴时,王慧敏,蒙胜军. 基于深度信念网络的文本情感分类研究*[J]. 数据分析与知识发现, 2019, 3(4): 71-79.
Qingqing Zhang,Xingshi He,Huimin Wang,Shengjun Meng. Text Sentiment Classification Based on Deep Belief Network. Data Analysis and Knowledge Discovery, 2019, 3(4): 71-79.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2018.0516      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2019/V3/I4/71
[1] Liu B.Sentiment Analysis and Opinion Mining[M]. Morgan & Claypool Publishers, 2012.
[2] Cui Z Y, Cao Z J, Yang J Y, et al. Hierarchical Recognition System for Target Recognition from Sparse Representations[J]. Mathematical Problems in Engineering, 2015: Article ID 527095.
[3] 张庆庆, 刘西林. 基于依存句法关系的文本情感分类研究[J]. 计算机工程与应用, 2015, 51(22): 28-32.
[3] (Zhang Qingqing, Liu Xilin.Sentiment Analysis Based on Dependency Sytactic Relation[J]. Computer Engineering and Applications, 2015, 51(22): 28-32.)
[4] Balahur A, Turchi M.Comparative Experiments Using Supervised Learning and Machine Translation for Multilingual Sentiment Analysis[J]. Computer Speech & Language, 2014, 28(1): 56-75.
[5] Mleczko W K, Kapuscinski T, Nowicki R K.Rough Deep Belief Network - Application to Incomplete Handwritten Digits Pattern Classification[J]. Information and Software Technologies, 2015, 538: 400-411.
[6] Zhao Q N, Ma J J, Gong M G, et al.Three-Class Change Detection in Synthetic Aperture Radar Images Based on Deep Belief Network[J]. Journal of Computational and Theoretical Nanoscience, 2016, 13(6): 3757-3762.
[7] Dahl G E, Yu D, Deng L, et al.Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition[J]. IEEE Transactions on Audio, Speech, and Language Processing, 2012, 20(1): 30-42.
[8] Zhou G, Zeng Z, Huang J X, et al.Transfer Learning for Cross-Lingual Sentiment Classification with Weakly Shared Deep Neural Networks[C]// Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, Pisa, Italy. New York, USA: ACM, 2016: 245-254.
[9] Mikolv T, Chen K, Corrado G, et al. Efficient Estimation of Word Representation in Vector Space[OL]. arXiv Preprint, arXiv:1301.3781, 2013.
[10] Ruangkanokman P, Achalakul T, Akkarajitsakul K.Deep Belief Networks with Feature Selection for Sentiment Classification[C]// Proceedings of the 7th International Conference on Intelligent Systems, Modelling and Simulation. 2016: 25-27.
[11] Hinton G E, Salakhutdinov R R.Reducing the Dimensionality of Data with Neural Networks[J]. Science, 2006, 313(5786): 504-507.
[12] Zeng N, Wang Z, Zhang H, et al.Deep Belief Networks for Quantitative Analysis of a Gold Immunochromatograpghic Strip[J]. Cognitive Computation, 2016, 8(4): 684-692.
[13] Hinton G E.A Practical Guide to Training Restricted Boltzmann Machines[J]. Neural Networks: Tricks of the Trade, 2012, 7700: 599-619.
[14] Hinton G E.Training Products of Experts by Minimizing Contrastive Divergence[J]. Neural Computation, 2002, 14(8): 1771-1800.
[15] Rumelhart D E .Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1: Foundations[J]. Language, 1986, 63(4): 45-76.
[1] 张庆庆, 刘西林. 基于BPSO随机子空间的文本情感分类研究[J]. 数据分析与知识发现, 2017, 1(5): 71-81.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn