基于主题加权LDA模型的情感分类方法

王飞雪<sup>1</sup>,李芳<sup>2</sup>

doi:10.13718/j.cnki.xsxb.2018.09.007

西南师范大学学报(自然科学版)

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
	姓名不能为空！
邮箱
	邮箱不能为空！非法的邮箱地址。
手机号码
	电话不能为空！请输入有效手机号!
标题
	标题不能为空！
留言内容
	内容不能为空！
验证码
	验证码不能为空！验证码错误！

基于主题加权LDA模型的情感分类方法

王飞雪1,李芳2. 基于主题加权LDA模型的情感分类方法[J]. 西南师范大学学报(自然科学版), 2018, 43(9): 38-44. doi: 10.13718/j.cnki.xsxb.2018.09.007

引用本文:

王飞雪¹,李芳². 基于主题加权LDA模型的情感分类方法[J]. 西南师范大学学报(自然科学版), 2018, 43(9): 38-44. doi: 10.13718/j.cnki.xsxb.2018.09.007

WANG Fei-xue1, LI Fang2. Emotion Classification Method Based on Topic Weighted LDA Model[J]. Journal of Southwest China Normal University(Natural Science Edition), 2018, 43(9): 38-44. doi: 10.13718/j.cnki.xsxb.2018.09.007

Citation:

WANG Fei-xue¹, LI Fang². Emotion Classification Method Based on Topic Weighted LDA Model[J]. Journal of Southwest China Normal University(Natural Science Edition), 2018, 43(9): 38-44. doi: 10.13718/j.cnki.xsxb.2018.09.007

基于主题加权LDA模型的情感分类方法

王飞雪¹,李芳²

1. 重庆人文科技学院计算机工程学院, 重庆合川 401524;
2. 重庆大学计算机学院, 重庆 400044

Emotion Classification Method Based on Topic Weighted LDA Model

WANG Fei-xue¹, LI Fang²

1. School of Computer Engineering, Chongqing Institute of Humanities and Technology, Hechuan Chongqing 401524, China;
2. School of Computer Science, Chongqing University, Chongqing 400044, China

摘要: 针对LDA（Latent Dirichlet Allocation）主题模型生成的大量topic，很大部分topic内部词语相关度很低，可解释性差，对语言模型后的应用效果带来一定的影响.针对这一问题，该文提出了一种基于主题加权LDA模型的情感分类方法，该模型实现不同主题中内部相关的词语特征加权计算，能够消除不同主题内具有相关度词语的相互影响.实验结果表明，与传统LDA模型分类方法对比，该文提出的基于主题加权LDA模型的情感分类方法平均F1值提高了6.7%~8.1%，验证了该文提出的方法是有效的，提高了分类效果.
- LDA模型 /
- 特征加权 /
- 主题模型 /
- 情感分类
Abstract: For the large number of topics generated by the LDA (Latent Dirichlet Allocation) theme model, the relevance of the internal words is very low, poor interpretation, and the effect of the language model is affected. In order to solve this problem, an emotion classification method based on topic weighted LDA model has been proposed in this paper, which can realize the weighting calculation of words in different themes, and can eliminate the influence of words with relevance in different themes. The experimental results show that compared with the traditional LDA model classification method, the average F1 value of the emotion classification method based on the topic weighted LDA model is improved by 6.7%-8.1%, which proves that our proposed method is effective and improved classification effect.
- LDA model /
- weighted feature /
- topic model /
- emotion classification .

[1]	尹书华.基于复杂网络的微博用户关系网络特性研究[J].西南师范大学学报(自然科学版),2011,36(6):57-61.
[2]	孙平安,谭秋月.基于多属性决策理论的文本信息挖掘技术研究[J].西南师范大学学报(自然科学版),2016,41(11):155-159.
[3]	李红波,孟欣赏,吴渝, 等.Web访问挖掘中的匿名用户识别算法研究[J].西南师范大学学报(自然科学版),2015, 40(9):78-84.
[4]	SOCHER R,PENNINGTON J,HUANG E H,et al.Semi-supervised Recursive Autoencoders for Predicting Sentiment Distributions[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing.Edinburgh:Association for Computational Linguistics,2011.
[5]	TAI K S,SOCHER R,MANNING C D.Improved Semantic Representations from Tree-Structured Long Short-Term Memory Networks[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing. Beijing:ACL,2015.
[6]	LIU Y,LI S,ZHANG X,et al.Implicit Discourse Relation Classification via Multi-Task Neural Networks[C]//Proceedings of the Thirtieth Conference on the Association for the Advance of Artificial Intelligence. Phoenix:AAAL,2016.
[7]	程静,刘光远.基于情感心电信号的去趋势波动分析研究[J].西南大学学报(自然科学版),2016,38(2):169-175.
[8]	刘真臻, 徐东平.微博个性化标签图形化RTM模型Gibbs采样推荐[J].微电子学与计算机, 2017, 34(12):138-144.
[9]	张志昌,周慧霞,姚东任, 等.基于词向量的中文词汇蕴涵关系识别[J].计算机工程,2016,42(2):169-174.
[10]	李湘东,高凡,丁丛.LD A模型下不同分词方法对文本分类性能的影响研究[J].计算机应用研究,2017,34(1):62-66.
[11]	王见,陈义,邓帅.基于改进SVM分类器的动作识别方法[J].重庆大学学报(自然科学版),2016, 37(1):12-17.

计量

文章访问数: 782
HTML全文浏览数: 540
PDF下载数: 81
施引文献: 0

基于主题加权LDA模型的情感分类方法

王飞雪¹,李芳²

1. 重庆人文科技学院计算机工程学院, 重庆合川 401524;
2. 重庆大学计算机学院, 重庆 400044

收稿日期: 2017-07-05

关键词:

摘要: 针对LDA（Latent Dirichlet Allocation）主题模型生成的大量topic，很大部分topic内部词语相关度很低，可解释性差，对语言模型后的应用效果带来一定的影响.针对这一问题，该文提出了一种基于主题加权LDA模型的情感分类方法，该模型实现不同主题中内部相关的词语特征加权计算，能够消除不同主题内具有相关度词语的相互影响.实验结果表明，与传统LDA模型分类方法对比，该文提出的基于主题加权LDA模型的情感分类方法平均F1值提高了6.7%~8.1%，验证了该文提出的方法是有效的，提高了分类效果.

English Abstract

Emotion Classification Method Based on Topic Weighted LDA Model

1. 重庆人文科技学院计算机工程学院, 重庆合川 401524;
2. 重庆大学计算机学院, 重庆 400044

Received Date: 2017-07-05

Keywords:

Abstract: For the large number of topics generated by the LDA (Latent Dirichlet Allocation) theme model, the relevance of the internal words is very low, poor interpretation, and the effect of the language model is affected. In order to solve this problem, an emotion classification method based on topic weighted LDA model has been proposed in this paper, which can realize the weighting calculation of words in different themes, and can eliminate the influence of words with relevance in different themes. The experimental results show that compared with the traditional LDA model classification method, the average F1 value of the emotion classification method based on the topic weighted LDA model is improved by 6.7%-8.1%, which proves that our proposed method is effective and improved classification effect.