您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(理学版)》

山东大学学报(理学版) ›› 2018, Vol. 53 ›› Issue (9): 35-39.doi: 10.6040/j.issn.1671-9352.1.2017.003

• • 上一篇    下一篇

结合新闻和评论文本的读者情绪分类方法

严倩,王礼敏,李寿山*,周国栋   

  1. 苏州大学自然语言处理实验室, 江苏 苏州 215006
  • 收稿日期:2017-07-04 出版日期:2018-09-20 发布日期:2018-09-10
  • 作者简介:严倩(1993— ),女,硕士研究生,研究方向为自然语言处理. E-mail:qyan@stu.suda.edu.cn*通信作者简介:李寿山(1980— ),男,博士,教授,研究方向为自然语言处理. E-mail:lishoushan@suda.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(61331011,61672366,61375073)

Reader emotion classification with news and comments

  1. Natural Language Processing Laboratory, Soochow University, Suzhou 215006, Jiangsu, China
  • Received:2017-07-04 Online:2018-09-20 Published:2018-09-10

摘要: 新闻和评论文本是进行读者情绪分类的重要资源,但仅仅使用新闻和文本或者把2类文本进行混合作为一组总体特征,不能充分利用不同文本特征间的区别和联系。基于此,提出了一种双通道LSTM(long short-term memory)方法,该方法把2类文本作为2组特征,分别用单通道LSTM神经网络学习这2组特征文本得到文本的LSTM表示,然后通过联合学习的方法学习这2组特征间的关系。实验结果表明,该方法能有效提高读者情绪的分类性能。

关键词: 联合学习, 读者情绪分类, 双通道LSTM

Abstract: The news and comments are important resources to classify the reader emotion. However, previous studies only used news texts or mixed two types of texts as a general feature, which did not make the best use of the differences and connections between different textual features. Based on it, the paper proposed a new approach named dual-channel LSTM, which treated two types of texts as different features. First, the approach learned a LSTM representation with a LSTM recurrent neural network. Then, it proposed a joint learning method to learn the relationship between the features. Empirical studies demonstrate the effectiveness of the proposed approach to reader emotion classification.

Key words: reader emotion classification, joint learning, dual-channel LSTM

中图分类号: 

  • TP391
[1] CHEN Ying, LEE S Y M, LI Shoushan, et al. Emotion cause detection with linguistic constructions[C] //Proceeding of the 23rd International Conference on Computation Linguistics. Stroudsburg: Association for Computational Linguistics(EMNLP'11), 2011:179-187.
[2] PURVER M, BATTERSBY S. Experimenting with distant supervision for emotion classification[C] //Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics(EACL'12). Stroudsburg: Association for Computational Linguistics, 2012:482-491.
[3] 刘欢欢. 面向新闻的读者情绪自动分析研究方法[D]. 苏州:苏州大学, 2015. LIU Huanhuan. Automatic classification on readers emotion towards news[D]. Suzhou: Soochow University, 2015.
[4] LIN H Y, CHEN H H. Ranking reader emotions using pairwise loss minimization and emotional distribution regression[C] //Proceedings of the Conference on Empirical Methods in Natural Language Processing(EMNLP08). Stroudsburg: Association for Computational Linguistics, 2008:136-144.
[5] LIU Huanhuan, LI Shoushan, ZHOU Guodong, et al. Joint modeling of news readers and comment writers emotions[C] //Meeting of the Association for Computational Linguistics. Sofia: Association for Computational Linguistics, 2013: 511-515.
[6] BAI S, NING Y, YUAN S, et al. Predicting readers emotion on Chinese Web news articles[C] //International Conference on Pervasive Computing and the Networked World. Berlin: International Conference on Pervasive Computing and the Networked World, 2012: 16-27.
[7] XU R F, ZOU C T, XU J. Readers emotion prediction based on partitioned latent dirichlet allocation model[C] //Proceedings of the 2012 International Conference on Pervasive Computing and the Networked World(ICPCA/SWS'12). Heidelberg: Springer-Verlag, 2013: 17-31.
[8] LIN K H, YANG CHANGHUA, CHEN H. What emotions do news articles trigger in their readers?[C] //Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval(SIGIR'07).New York: ACM, 2007: 733-734.
[9] LIN K H, YANG Changhua, CHEN H. Emotion classification of online news articles from the readers perspective[C] //Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology(WI-IAT'08). Washington: IEEE Computer Society, 2008: 220-226.
[10] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
[11] GRAVES A. Supervised sequence labelling with recurrent neural networks[M]. Berlin Heidelberg: Springer, 2012:4-12.
[12] HINTON G E, SRIVASTAVA N, KRIZHEVSKY A, et al. Improving neural networks by preventing co-adaptation of feature detectors[J]. Computer Science, 2012, 3(4):212-223.
[1] 龚双双,陈钰枫,徐金安,张玉洁. 基于网络文本的汉语多词表达抽取方法[J]. 山东大学学报(理学版), 2018, 53(9): 40-48.
[2] 余传明,左宇恒,郭亚静,安璐. 基于复合主题演化模型的作者研究兴趣动态发现[J]. 山东大学学报(理学版), 2018, 53(9): 23-34.
[3] 原伟,唐亮,易绵竹. 基于本体的俄文新闻话题检测设计与实现[J]. 山东大学学报(理学版), 2018, 53(9): 49-54.
[4] 廖祥文,张凌鹰,魏晶晶,桂林,程学旗,陈国龙. 融合时间特征的社交媒介用户影响力分析[J]. 山东大学学报(理学版), 2018, 53(3): 1-12.
[5] 余传明,冯博琳,田鑫,安璐. 基于深度表示学习的多语言文本情感分析[J]. 山东大学学报(理学版), 2018, 53(3): 13-23.
[6] 张军,李竞飞,张瑞,阮兴茂,张烁. 基于网络有效阻抗的社区发现算法[J]. 山东大学学报(理学版), 2018, 53(3): 24-29.
[7] 庞博,刘远超. 融合pointwise及深度学习方法的篇章排序[J]. 山东大学学报(理学版), 2018, 53(3): 30-35.
[8] 陈鑫,薛云,卢昕,李万理,赵洪雅,胡晓晖. 基于保序子矩阵和频繁序列模式挖掘的文本情感特征提取方法[J]. 山东大学学报(理学版), 2018, 53(3): 36-45.
[9] 王彤,马延周,易绵竹. 基于DTW的俄语短指令语音识别[J]. 山东大学学报(理学版), 2017, 52(11): 29-36.
[10] 张晓东,董唯光,汤旻安,郭俊锋,梁金平. 压缩感知中基于广义Jaccard系数的gOMP重构算法[J]. 山东大学学报(理学版), 2017, 52(11): 23-28.
[11] 孙建东,顾秀森,李彦,徐蔚然. 基于COAE2016数据集的中文实体关系抽取算法研究[J]. 山东大学学报(理学版), 2017, 52(9): 7-12.
[12] 王凯,洪宇,邱盈盈,王剑,姚建民,周国栋. 一种查询意图边界检测方法研究[J]. 山东大学学报(理学版), 2017, 52(9): 13-18.
[13] 张帆,罗成,刘奕群,张敏,马少平. 异质搜索环境下的用户偏好性预测方法研究[J]. 山东大学学报(理学版), 2017, 52(9): 26-34.
[14] 杨艳,徐冰,杨沐昀,赵晶晶. 一种基于联合深度学习模型的情感分类方法[J]. 山东大学学报(理学版), 2017, 52(9): 19-25.
[15] 原伟,易绵竹. 基于维基百科的俄汉可比语料库构建及可比度计算[J]. 山东大学学报(理学版), 2017, 52(9): 1-6.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!