基于情感词和多任务卷积神经网络的文本情感分布学习

PDF(5193 KB)

中文信息学报 ›› 2023, Vol. 37 ›› Issue (4) : 126-136.

情感分析与社会计算

江晨琳,曾雪强,郭小奉,东雨畅,左家莉,王明文

作者信息 +

Text Emotion Distribution Learning Based on Lexicon Enhanced Multi-Task CNN

JIANG Chenlin, ZENG Xueqiang, GUO Xiaofeng, DONG Yuchang, ZUO Jiali, WANG Mingwen

Author information +

History +

摘要

不同于传统的情感分析范式,情感分布学习采用与示例关联的情感分布对多种情绪进行定量建模,可以较好地处理具有情绪模糊性的情感分析任务。针对现有情感分布学习方法缺乏考虑文本分析任务特有的情感词语言学先验知识的问题,该文提出一种基于情感词和多任务卷积神经网络(Lexicon enhanced Multi-Task Convolutional Neural Network, LMT-CNN)的文本情感分布学习模型,用于预测文本的情感分布和情绪标签。LMT-CNN模型的网络结构由文本语义信息模块、情感词的情感知识模块和多任务预测模块组成,采用端到端方式进行模型训练和预测。在7个常用的文本情感数据集上的对比实验结果表明,LMT-CNN模型具有比已有的情感分布学习方法更优的情感分布预测和情绪分类性能。

Abstract

Different from traditional sentiment analysis paradigms, emotion distribution learning quantitatively models multiple emotions through the emotion distribution associated with examples, which can better deal with the sentiment analysis tasks with emotion fuzziness. This paper proposes a text emotion distribution learning model based on Lexicon enhanced Multi-Task Convolutional Neural Network (LMT-CNN) to predict text emotion distribution and emotion labels. The LMT-CNN model consists of a semantic information module, a sentiment knowledge module based on affective words and a multi-task prediction module to predict emotion distribution in an end-to-end manner. Extensive experiments on 7 datasets show that the proposed model is superior to the existing methods in text emotion distribution prediction and emotion classification tasks.

导出引用

江晨琳,曾雪强,郭小奉,东雨畅,左家莉,王明文. 基于情感词和多任务卷积神经网络的文本情感分布学习. 中文信息学报. 2023, 37(4): 126-136

JIANG Chenlin, ZENG Xueqiang, GUO Xiaofeng, DONG Yuchang, ZUO Jiali, WANG Mingwen. Text Emotion Distribution Learning Based on Lexicon Enhanced Multi-Task CNN. Journal of Chinese Information Processing. 2023, 37(4): 126-136

参考文献

[1] LIU T, DU Y, ZHOU Q. Text emotion recognition using GRU neural network with attention mechanism and emoticon emotions[C]//Proceedings of the 2nd International Conference on Robotics, Intelligent Control and Artificial Intelligence. Shanghai, China: ACM, 2020: 278-282.
[2] YADOLLAHI A, SHAHRAKI A G, ZAIANE O R. Current state of text sentiment analysis from opinion to emotion mining[J]. ACM Computing Surveys, 2017, 50(2): 1-33.
[3] 韩鹏宇,高盛祥,余正涛等. 基于案件要素指导的涉案舆情新闻文本摘要方法[J]. 中文信息学报, 2020, 34(5): 56-63,73.
[4] 陈放,王颗,梁爽,等. 面向商品评论的二元情感认知模型[J]. 中文信息学报, 2018, 32(8): 135-142.
[5] WANG W, ZHU K, WANG H, et al. The impact of sentiment orientations on successful crowdfunding campaigns through text analytics[J]. IET Software, 2017, 11(5): 229-238.
[6] ZHANG L, WANG S, LIU B. Deep learning for sentiment analysis: A survey[J]. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2018,8(4): e1253.
[7] GENG X. Label distribution learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2016, 28(7): 1734-1748.
[8] 曾雪强,罗明珠,陈素芬,等. 基于自适应多重多元回归的人脸年龄估计[J]. 江西师范大学学报(自然科学版),2019,43(01): 68-75.
[9] ZHOU D, ZHANG X, ZHOU Y, et al. Emotion distribution learning from texts[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Austin, Texas: Association for Computational Linguistics, 2016: 638-647.
[10] ZHAO Z, MA X. Text emotion distribution learning from small sample: a meta-learning approach[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Hong Kong, China, 2019: 3955-3965.
[11] JIA X, ZHENG X, LI W, et al. Facial emotion distribution learning by exploiting low-rank label correlations locally[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019: 9833-9842.
[12] PANG J, RAO Y, XIE H, et al. Fast supervised topic models for short text emotion detection[J]. IEEE Transactions on Cybernetics, 2021, 51(2): 815-828.
[13] TENG Z, VO D T, ZHANG Y. Context-sensitive lexicon features for neural sentiment analysis[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Austin, Texas: Association for Computational Linguistics, 2016: 1629-1638.
[14] ZHANG Y, FU J, SHE D, et al. Text emotion distribution learning via multi-task convolutional neural network[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm, Sweden: International Joint Conferences on Artificial Intelligence Organization, 2018: 4595-4601.
[15] TONG R M. An operational system for detecting and trackingopinions in online discussion[C]//Proceedings of SIGIR Workshop on Operational Text Classification. New York: ACM, 2001: 1-6.
[16] GAO B B, XING C, XIE C W, et al. Deep label distribution learning with label ambiguity[J]. IEEE Transactions on Image Processing, 2017, 26: 2825-2838.
[17] STRAPPARAVA C, MIHALCEA R. SemEval-2007 task 14: Affective text[C]//Proceedings of the 4th International Workshop on Semantic Evaluations-SemEval. Prague, Czech Republic: Association for Computational Linguistics, 2007: 70-74.
[18] QUAN C, REN F. A blog emotion corpus for emotional expression analysis in Chinese[J]. Computer Speech & Language, 2010, 24(4): 726-749.
[19] ALM C O, SPROAT R. Emotional sequencing and development in fairy tales[C]//Proceedings of the 1st International Conference on Affective Computing and Intelligent Interaction. Beijing, China, 2005: 668-674.
[20] MOHAMMAD S. Emotional tweets[C]//Proceedings of the 1st Joint Conference on Lexical and Computational Semantics. Montreal, Canada, 2012: 246-255.
[21] SHAHRAKI A G. Emotion mining from text[D]. Canada: University of Alberta, 2015.
[22] SCHERER K R, WALLBOTT H G. Evidence for universality and cultural variation of differential emotion response patterning[J]. Journal of Personality and Social Psychology, US: American Psychological Association, 1994, 66(2): 310-328.
[23] 姚源林,王树伟,徐睿峰等. 面向微博文本的情绪标注语料库构建[J]. 中文信息学报, 2014, 28(05): 83-91.
[24] SOCHER R, PERELYGIN A, WU J, et al. Recursive deep models for semantic compositionality over a sentiment treebank[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Washington, USA: EMNLP, 2013: 1631-1642.
[25] ZHENG X, JIA X, LI W. Label Distribution learning by exploiting sample correlations locally[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence, the 30th Innovative Applications of Artificial Intelligence, and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence, 2018: 4556-4563.
[26] QIN X, CHEN Y, RAO Y, et al. A constrained optimization approach for cross-domain emotion distribution learning[J]. Knowledge-Based Systems, 2021, 227: 107160.
[27] WANG Y. Detecting emotions in social media: a con-strained optimization approach[C]//Proceedings of the 24th International Conference on Artificial Intelligence. Buenos Aires, Argentina, 2015: 996-1002.
[28] ADBI A, SHAMSUDDIN S M, HASAN S, et al. Deep learning-based sentiment classification of evaluative text based on multi-feature fusion[J]. Information Processing & Management, 2019, 56(4): 1245-1259.
[29] KE P, JI H, LIU S, et al. SentiLARE: Sentiment-aware language representation learning with linguistic knowledge[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Online: Association for Computational Linguistics, 2020: 6975-6988.
[30] ROBBINS H, MONRO S. A stochastic approximation method[J]. Annals of Mathematical Statistics, 1951, 22(3): 400-407.
[31] PORIA S, GELBUKH A, CAMBRIA E, et al. EmoSenticSpace: A novel framework for affective common-sense reasoning[J]. Knowledge-Based Systems, 2014, 69: 108-123.
[32] MOHAMMAD S M, TURNEY P D. NRC emotion lexicon[J]. National Research Council of Canada: Technical Report, 2013, 2009-94.
[33] 徐琳宏,林鸿飞,潘宇等. 情感词汇本体的构造[J]. 情报学报,2008, 27(2): 180-185.
[34] KIM Y. Convolutional neural networks for sentence classification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Doha, Qatar: Association for Computational Linguistics, 2014: 1746-1751.
[35] ZHANG M L, ZHOU Z H. Multi-label learning by instance differentiation[C]//Proceedings of the 22nd National Conference on Artificial Intelligence. Vancouver, British Columbia, Canada: AAAI, 2007, 1: 669-674.

基金

国家自然科学基金(62266021,61866017,61866018,61876074,61966019);江西省自然科学基金(20192BAB207027)

PDF(5193 KB)

Accesses

Citation

Detail

段落导航

摘要
Abstract
关键词
Key words
引用本文
参考文献
基金

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

{{custom_fnGroup.title_cn}}

脚注

基金



Issue Date
2023-06-21