基于主题种子词的情感分析方法

doi:10.11772/j.issn.1001-9081.2015.09.2560

计算机应用 ›› 2015, Vol. 35 ›› Issue (9): 2560-2564.DOI: 10.11772/j.issn.1001-9081.2015.09.2560

基于主题种子词的情感分析方法

陈永恒¹, 左万利², 林耀进¹

1. 闽南师范大学计算机学院, 福建漳州 363000;
2. 吉林大学计算机科学与技术学院, 长春 130012

收稿日期:2015-03-31 修回日期:2015-05-11 出版日期:2015-09-10 发布日期:2015-09-17
通讯作者: 陈永恒(1980-),男,黑龙江大庆人,讲师,博士,主要研究方向:机器学习、数据挖掘、推荐系统,cyh771@163.com
作者简介:左万利(1957-),男,吉林长春人,博士生导师,博士,主要研究方向:数据库优化、数据挖掘、搜索引擎;林耀进(1981-),男,福建漳州人,副教授,博士,主要研究方向:数据集成、数据挖掘。
基金资助:
国家自然科学基金资助项目(61303131,60373099,60973040);福建省教育厅省中青年教师教育科研项目(JA13196)。

Sentiment-aspect analysis method based on seed words

CHEN Yongheng¹, ZUO Wanli², LIN Yaojing¹

1. College of Computer Science, Minnan Normal University, Zhangzhou Fujian 363000, China;
2. College of Computer Science and Technology, Jilin University, Changchun Jilin 130012, China

Received:2015-03-31 Revised:2015-05-11 Online:2015-09-10 Published:2015-09-17

摘要/Abstract

摘要： 产品或服务的情感主题分析,有利于用户从海量的评论集中快速地了解到自己关注产品或服务的主题情感信息。针对现存非监督情感分析模型情感主题发现性能不足的问题,提出了一种的基于主题种子词的情感分析方法,该方法在自动构建领域主题种子词及主题文本基础上,利用主题种子词监督的情感分析模型(SAA_SSW)实现主题及其关联情感的联合发现。实验结果表明,相比传统的情感/主题联合模型(JST)和主题情感统一模型(ASUM),SAA_SSW能够识别出相同的词在不同的主题下具有的情感标签,挖掘的情感词与主题之间的相关度更高;另外,基于不同情感字典进行分类精度分析,SAA_SSW的分类精度相对于这两种模型至少提高7.5%。所以,SAA_SSW模型能很好地完成情感主题的发现,以及具有较高的情感分类精度。

关键词: 隐藏狄利克雷分配, 文本分析, 主题模型, 自然语言处理

Abstract: The analysis of sentiment-aspect for product or service is useful for finding the information of sentiment-aspect from the mess of comment set. This paper proposed a new method of sentiment-aspect based on seed words of aspect. Firstly, seed words of aspect and documents of aspect automatically could be achieved by this method. Secondly, Sentiment-Aspect Analysis model Supervised by Seed Words (SAA_SSW) was employed by this method to find aspect and related sentiment. The experimental results show that, compared with traditional Joint Sentiment/Topic Model (JST) and Aspect and Sentiment Unification Model (ASUM), SAA_SSW can find the sentiment labels for same word under different topics and achieve higher relevance between sentiment word and topic. In addition, SAA_SSW model, compared with traditional JST and ASUM model, can improve the classification accuracy by at least 7.5%. So, SAA_SSW model can achieve the extraction of sentiment-aspect well and improve the classification accuracy.

Key words: Latent Dirichlet Allocation (LDA), text analysis, topic model, natural language processing

中图分类号:

陈永恒, 左万利, 林耀进. 基于主题种子词的情感分析方法[J]. 计算机应用, 2015, 35(9): 2560-2564.

CHEN Yongheng, ZUO Wanli, LIN Yaojing. Sentiment-aspect analysis method based on seed words[J]. Journal of Computer Applications, 2015, 35(9): 2560-2564.

参考文献

[1] ZHANG Q, QU Y. Topic-opposite sentiment mining model for online review analysis [J].Journal of Frontiers of Computer Science and Technology, 2013,7(7):620-629.(张倩,瞿有利.用于网络评论分析的主题-对立情感挖掘模型[J].计算机科学与探索,2013,7(7):620-629.)
[2] MOGHADDAM S, ESTER M. Aspect-based opinion mining from online reviews [C]. Tutorial at SIGIR Conference, 2012. MOGHADDAM S, ESTER M. Aspect-based opinion mining from online reviews [EB/OL]. [2015-02-02]. http://www.docin.com/p-543993078.html.
[3] MOGHADDAM S, ESTER M. The FLDA model for aspect-based opinion mining: addressing the cold start problem [C]//Proceedings of the 22nd International Conference on World Wide Web. Geneva:Canton of Geneva, 2013:909-918.
[4] NEWMAN D, ASUNXION A, SMYTH P, et al. Distributed inference for latent Dirichlet allocation [J]. In Neural Information Processing Systems, 2007,14(7):135-142. NEWMAN D, ASUNXION A, SMYTH P, et al. Distributed inference for latent Dirichlet allocation [EB/OL]. [2015-02-02]. http://ciir.cs.umass.edu/wiki/pub/Main/791mtSpring09/distributed_topic_modeling.pdf.
[5] BLEI D M, NG A Y, JORDAN M I. Latent Dirichlet allocation [J]. Journal of Machine Learning Research, 2003,12(6):993-1022.
[6] SUN Y, ZHOU X, FU W. Unsupervised topic and sentiment unification model for sentiment analysis [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2013,49(1):102-108. (孙艳,周学广,付伟.基于主题情感混合模型的无监督文本情感分析[J].北京大学学报:自然科学版, 2013,49(1):102-108.)
[7] LU Y, ZHAI C. Opinion integration through semi-supervised topic modeling [C]//Proceeding of the 17th international conference on World Wide Web.2008: 121-130. LU Y, ZHAI C. Opinion integration through semi-supervised topic modeling [EB/OL]. [2015-01-02]. http://sifaka.cs.uiuc.edu/~yuelu2/pub/www08-opinion.pdf.
[8] JO Y, OH A H. Aspect and sentiment unification model for online review analysis [C]//Proceedings of the 4th ACM International Conference on Web Search and Data Mining. New York: ACM, 2011:815-824.
[9] SHAN B, LI F. A survey of topic evolution based on LDA [J]. Journal of Chinese Information Processing, 2010,24(6):43-49.(单斌,李芳.基于LDA话题演化研究方法综述[J]. 中文信息学报,2010,24(6):43-49.)
[10] LIN C, HE Y. Joint sentiment/topic model for sentiment analysis [C]//Proceedings of the 18th ACM Conference on Information and Knowledge Management. New York: ACM, 2009:375-384.
[11] HEINRICH G. Parameter estimation for text analysis [EB/OL].[2010-10-10]. http://www.arbylon.net/publications/text-est.pdf.
[12] PANF B, LEE L. Thumbs up: sentiment classification using machine learning techniques [C]//Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: Association for Computational Linguistics, 2002:79-86.
[13] MASE F, COLLIGONO A, VANDERMEULEN D, et al. Multimodality image registration by maximization of mutual information [J]. IEEE Transactions on Medical Imaging, 1997,16(2):187-198.
[14] WILSON T, WIEBE J, HOFFMANN P. Recognizing contextual polarity in phrase-level sentiment analysis [C]//The conference on Human Language Technology and Empirical Methods in Natural Language Processing, Vancouver, British Columbia, Canada: ACL.2005.WILSON T, WIEBE J, HOFFMANN P. Recognizing contextual polarity in phrase-level sentiment analysis [EB/OL]. [2014-12-10]. http://aclweb.org/anthology/H/H05/H05-1044.pdf.

[1]	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.
[2]	刘雅璇, 钟勇. 基于头实体注意力的实体关系联合抽取方法[J]. 计算机应用, 2021, 41(9): 2517-2522.
[3]	周险兵, 樊小超, 任鸽, 杨勇. 基于多层次语义特征的英文作文自动评分方法[J]. 计算机应用, 2021, 41(8): 2205-2211.
[4]	刘睿珩, 叶霞, 岳增营. 面向自然语言处理任务的预训练模型综述[J]. 计算机应用, 2021, 41(5): 1236-1246.
[5]	王朱君, 王石, 李雪晴, 朱俊武. 基于深度学习的事件因果关系抽取综述[J]. 计算机应用, 2021, 41(5): 1247-1255.
[6]	李雪晴, 王石, 王朱君, 朱俊武. 自然语言生成综述[J]. 计算机应用, 2021, 41(5): 1227-1235.
[7]	李文惠, 曾上游, 王金金. 基于改进注意力机制的图像描述生成算法[J]. 计算机应用, 2021, 41(5): 1262-1267.
[8]	杨丰瑞, 霍娜, 张许红, 韦巍. 基于注意力机制的主题扩展情感对话生成[J]. 计算机应用, 2021, 41(4): 1078-1083.
[9]	杨璐, 何明祥. 基于门控机制和卷积神经网络的中文文本情感分析模型[J]. 计算机应用, 2021, 41(10): 2842-2848.
[10]	杨威亚, 余正涛, 高盛祥, 宋燃. 基于跨语言神经主题模型的汉越新闻话题发现方法[J]. 计算机应用, 2021, 41(10): 2879-2884.
[11]	朱思淼, 魏世伟, 魏思恒, 余敦辉. 基于弹幕情感分析和主题模型的视频推荐算法[J]. 计算机应用, 2021, 41(10): 2813-2819.
[12]	尹春勇, 章荪. 面向短文本情感分类的端到端对抗变分贝叶斯方法[J]. 计算机应用, 2020, 40(9): 2536-2542.
[13]	田保军, 刘爽, 房建东. 融合主题信息和卷积神经网络的混合推荐算法[J]. 计算机应用, 2020, 40(7): 1901-1907.
[14]	杨国峰, 杨勇. 基于BERT的常见作物病害问答系统问句分类[J]. 计算机应用, 2020, 40(6): 1580-1586.
[15]	赵亚欧, 张家重, 李贻斌, 付宪瑞, 生伟. 融合基于语言模型的词嵌入和多尺度卷积神经网络的情感分析[J]. 计算机应用, 2020, 40(3): 651-657.

基于主题种子词的情感分析方法

Sentiment-aspect analysis method based on seed words

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