基于迁移学习的唐诗宋词情感分析

doi:10.3969/j.issn.0372-2112.2016.11.030

电子学报 ›› 2016, Vol. 44 ›› Issue (11): 2780-2787.DOI: 10.3969/j.issn.0372-2112.2016.11.030

基于迁移学习的唐诗宋词情感分析

吴斌, 吉佳, 孟琳, 石川, 赵惠东, 李仪清

北京邮电大学智能通信软件与多媒体北京市重点实验室, 北京 100876

收稿日期:2015-02-13 修回日期:2015-07-01 出版日期:2016-11-25
- 作者简介:
- 吴斌,男,1969年生,湖南长沙人,教授、博士生导师.2002年中国科学院计算技术研究所博士毕业.主要从事复杂网络、数据挖掘、海量数据并行处理、可视分析、电信客户关系管理等方面的研究工作.E-mail:wubin@bupt.edu.cn;吉佳,女,1989年生,辽宁鞍山人,北京邮电大学硕士研究生.主要研究领域为数据挖掘与物联网大数据;孟琳,女,1993年生,山东莱芜人,2015年在北京邮电大学获学士学位,现为北京邮电大学计算机学院硕士研究生.主要研究领域为数据挖掘.
- 基金资助:
- 国家973重点基础研究发展计划 (No.2013CB329606）; 国家自然科学基金 (No.71231002，No.61375058）

Transfer Learning Based Sentiment Analysis for Poetry of the Tang Dynasty and Song Dynasty

WU Bin, JI Jia, MENG Lin, SHI Chuan, ZHAO Hui-dong, LI Yi-qing

Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2015-02-13 Revised:2015-07-01 Online:2016-11-25 Published:2016-11-25

摘要/Abstract

摘要：

随着计算社会学的兴起，利用数据挖掘分析社会情感是近期的研究重点.当前的研究主要针对现代文本，对于古代诗歌这类短文本的情感分析相对较少.本文提出了一个基于短文本特征扩展的迁移学习模型CATL-PCO，通过分析诗歌情感对当时社会及文化进行进一步了解.该模型首先基于频繁词对对古文特征向量进行扩展，再通过迁移学习方式，建立三个分类器并投票得出最后的情感分析结果.CATL-PCO模型首先能够解决古文短文本特征稀疏的问题，在此基础上进一步解决由于现代译文信息匮乏所导致的古代诗歌情感分析困难问题，从而准确的分析古诗词情感倾向，从计算社会学的角度，增进对中国历史的认识.实验表明，当训练集为中国唐诗时，本文提出方法能够准确的对唐代诗歌进行情感分类，并能应用于唐代和宋代各个时期情感分析及代表流派分析.

关键词: 情感分析, 社会计算学, 唐诗宋词, 迁移学习

Abstract:

With the rise of computational social science,analyzing social sentiment with data mining methods has attracted widespread attention and has become a hot spot in recent years.Existing researches of sentiment analysis mainly focus on modern text,but hardly involve the ancient short text literature.This paper proposes a short text feature extension based transfer learning model CATL-PCO(Correlation Analysis Transfer Learning-Probability Co-occurrence).Through sentiments analysis in ancient literature,this paper can discovery social and cultural development in the ancient era.CATL-PCO expands the ancient literature feature vector based on the frequent word pairs,and utilizes transfer learning method to train three sentiment classifiers.CATL-PCO solves the problem of sparsity of short text feature vector,and the scarcity of modern translation,which improves the cognition of Chinese History.Experiments demonstrate the effectiveness of the proposed method on the dataset of Chinese poems in Tang Dynasty.Moreover,different periods of Tang and Song Dynasty,and different genres are analyzed in this paper in details.

Key words: sentiment analysis, computational social science, poetries of the Tang dynasty and Song dynasty, transfer learning

中图分类号:

TP393

吴斌, 吉佳, 孟琳, 石川, 赵惠东, 李仪清. 基于迁移学习的唐诗宋词情感分析[J]. 电子学报, 2016, 44(11): 2780-2787.

WU Bin, JI Jia, MENG Lin, SHI Chuan, ZHAO Hui-dong, LI Yi-qing. Transfer Learning Based Sentiment Analysis for Poetry of the Tang Dynasty and Song Dynasty[J]. Acta Electronica Sinica, 2016, 44(11): 2780-2787.

参考文献

[1] DLazer,A S Pentland,L.Adamic,S Aral,et al.Life in the network:the coming age of computational social science[J].Science,2009,323(5915):721.
[2] Nakov P,Kozareva Z,Ritter A,et al.Semeval-2013 task 2:Sentiment analysis in twitter[A].In Proceedings of the International Workshop on Semantic Evaluation(SemEval 2013)[C].Dublin:Association for Computational Linguistics,2013.312-320.
[3] Fu X,Liu G,Guo Y,et al.Multi-aspect sentiment analysis for Chinese online social reviews based on topic modeling and HowNet lexicon[J].Knowledge-Based Systems,2013,37:186-195.
[4] 刘楠.面向微博短文本的情感分析研究[D].武汉大学,2013. LIU Nan,The research of microblogging short text oriented sentiment analysis[D].Wuhan Univeristy,2013.(in Chinese)
[5] Michel J B,Shen Y K,Aiden A P,et al.Quantitative analysis of culture using millions of digitized books[J].Science,2011,331(6014):176-182.
[6] Dong Z,Dong Q.HowNet-a hybrid language and knowledge resource[A].Natural Language Processing and Knowledge Engineering[C].IEEE,2003.820-824.
[7] Liang J,Tan J,Zhou X,et al.Dependency Expansion Model for Sentiment Lexicon Extraction[A],Web Intelligence (WI) and Intelligent Agent Technologies (IAT),2013 IEEE/WIC/ACM International Joint Conferences on[C].IEEE,2013,3:62-65.
[8] Liu B.Sentiment analysis and opinion mining[J].Synthesis Lectures on Human Language Technologies,2012,5(1):1-167.
[9] 张景祥,王士同,邓赵红,等.具有协同约束的共生迁移学习算法研究[J].电子学报,2014,42(3):556-560. ZHANG Jing-xiang,WANG Shi-tong,DENG Zhao-hong,et al.Symbiosis transfer learning method with collaborative constraints[J].Acta Electronica Sinica,2014,42(3):556-560.(in Chinese)
[10] Pan S J,Kwok J T,Yang Q.Transferlearning via dimensionality reduction[A],Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence[C].AAAI Press,2008.677-682.
[11] Gu Q,Zhou J.Learning the shared subspace for multi-task clustering and transductive transfer classification[A].Data Mining,2009.ICDM'09.Ninth IEEE International Conference on[C].IEEE,2009.159-168.
[12] R Mihalcea,C Corley,C Strapparava.Corpus-based and knowledge-based measures of text semantic similarity[A].In Proceedings of the 21st National Conference on Artificial Intelligence-Volume 1[C].AAAI Press,2006.775-780.
[13] Zhao Huidong,Wu Bin.Sentiment analysis based on transfer learning for Chinese ancient literature[A].Behavior,Economic and Social Computing (BESC),2014 International Conference on[C].IEEE,2014.1-7.
[14] Xuan-Hieu Phan,Cam-Tu Nguyen,Dieu-Thu Le,Le-Minh Nguyen,Susumu Horiguchi,Quang-Thuy Ha.A hidden topic-based framework toward building applications with short web documents[J].IEEE Transactions on Knowledge & Data Engineering,2011,23(7):961-976.
[15] X-H Phan,L-M Nguyen,S.Horiguchi.Learning to classify short and sparse text & web with hidden topics from large-scale data collections[A].In Proceeding of the 17th international conference on World WideWeb,WWW'08[C].ACM,2008.91-100.
[16] Petersen H,Poon J.Enhancing short text clustering with small external repositories[A].Proceedings of the Ninth Australasian Data Mining Conference[C].Australian Computer Society,Inc,2011.79-90.

基于迁移学习的唐诗宋词情感分析

Transfer Learning Based Sentiment Analysis for Poetry of the Tang Dynasty and Song Dynasty

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]	邵志文, 周勇, 谭鑫, 马利庄, 刘兵, 姚睿. 基于深度学习的表情动作单元识别综述[J]. 电子学报, 2022, 50(8): 2003-2017.
[2]	李维刚, 甘平, 谢璐, 李松涛. 基于样本对元学习的小样本图像分类方法[J]. 电子学报, 2022, 50(2): 295-304.
[3]	陈文俊, 杨春玲. 图像压缩感知的特征域优化及自注意力增强神经网络重构算法[J]. 电子学报, 2022, 50(11): 2629-2637.
[4]	张小恒, 张馨月, 李勇明, 王品, 刘玉川. 面向帕金森病语音诊断的非监督两步式卷积稀疏迁移学习算法[J]. 电子学报, 2022, 50(1): 177-184.
[5]	李勇斌, 王彬, 邵高平, 邵帅. 一种基于RCGAN的水声通信信号降噪方法[J]. 电子学报, 2022, 50(1): 54-62.
[6]	唐焕玲, 郑涵, 刘艳红, 马思源, 窦全胜, 鲁明羽. Tr-SLDA:一种面向交叉领域的迁移主题模型[J]. 电子学报, 2021, 49(3): 605-613.
[7]	张锦, 李阳, 任传伦, 黄炼, 王帅辉, 段晔鑫, 潘志松, 谢钧. 基于帧间高级特征差分的跨场景视频前景分割算法[J]. 电子学报, 2021, 49(10): 2032-2040.
[8]	王格格, 郭涛, 余游, 苏菡. 基于生成对抗网络的无监督域适应分类模型[J]. 电子学报, 2020, 48(6): 1190-1197.
[9]	张红斌, 蒋子良, 熊其鹏, 武晋鹏, 邬任重, 袁天, 姬东鸿. 基于改进的有效区域基因选择与跨模态语义挖掘的图像属性标注[J]. 电子学报, 2020, 48(4): 790-799.
[10]	赵鹏, 王美玉, 纪霞, 刘慧婷. 基于张量表示的域适配的迁移学习中特征表示方法[J]. 电子学报, 2020, 48(2): 359-368.
[11]	权宇, 李志欣, 张灿龙, 马慧芳. 融合深度扩张网络和轻量化网络的目标检测模型[J]. 电子学报, 2020, 48(2): 390-397.
[12]	刘真, 田靖玉, 苑宝鑫, 孙永奇. 基于知识聚合和迁移的跨领域推荐算法[J]. 电子学报, 2020, 48(10): 1928-1932.
[13]	季鼎承, 蒋亦樟, 王士同. 基于域与样例平衡的多源迁移学习方法[J]. 电子学报, 2019, 47(3): 692-699.
[14]	余游, 冯林, 王格格, 徐其凤. 一种基于伪标签的半监督少样本学习模型[J]. 电子学报, 2019, 47(11): 2284-2291.
[15]	任卓君, 陈光, 卢文科. 基于N-gram特征的恶意代码可视化方法[J]. 电子学报, 2019, 47(10): 2108-2115.