融合情感轮注意力的情感分布学习

doi:10.3778/j.issn.1002-8331.2108-0356

摘要/Abstract

摘要： 情感分布学习是一种近年提出的有效的多情绪分析模型，其核心思路是通过情感分布记录示例在各个情绪上的表达程度，适于处理存在情绪模糊性的情感分析任务。针对现有的情感分布学习方法较少考虑情感心理学先验知识的问题，提出一种基于情感轮注意力的情感分布学习（emotion wheel attention based emotion distribution learning，EWA-EDL）模型。EWA-EDL模型为每种基本情绪生成一个描述情绪心理学相关性的先验情感分布，再通过注意力机制将基于情感轮的先验知识直接融入深度神经网络。EWA-EDL模型采用端到端的方式对深度网络进行训练，同时学习情感分布预测和情绪分类任务。EWA-EDL模型主要由5部分构成，分别为输入层、卷积层、池化层、注意力层和多任务损失层。在8个常用的文本情感数据集上的对比实验表明，EWA-EDL模型在情感分布预测和情绪分类任务上的性能均优于对比的情感分布学习方法。

关键词: 情感分布学习, 情感轮, 注意力机制, 情绪分类

Abstract: Emotion distribution learning（EDL） is a recently proposed effective model for multi-emotion analysis. The main idea is to record the expression degree on each emotion of examples by emotion distribution, which is appropriate for dealing with emotion analysis tasks with emotional ambiguity. An emotion wheel attention based emotion distribution learning（EWA-EDL） model is proposed to address the problem that existing EDL methods rarely consider the priori knowledge of emotional psychology. The EWA-EDL model generates a prior emotion distribution for each basic emotion describing the emotion psychological relevance, and incorporates the prior knowledge based on the emotion wheel into the deep neural network through an attention mechanism. The EWA-EDL model uses an end-to-end approach to train the deep network to learn both emotion distribution prediction and emotion classification tasks. The EWA-EDL model consists of five main components, namely, input layer, convolutional layer, pooling layer, attention layer, and multi-task loss layer. Comparative experiments on eight commonly used textual emotion datasets show that the EWA-EDL model outperforms comparative EDL methods on both emotion distribution prediction and emotion classification tasks.

Key words: emotion distribution learning, emotion wheel, attention mechanism, emotion classification

陈启凡, 曾雪强, 左家莉, 万中英, 王明文. 融合情感轮注意力的情感分布学习[J]. 计算机工程与应用, 2023, 59(4): 120-129.

CHEN Qifan, ZENG Xueqiang, ZUO Jiali, WAN Zhongying, WANG Mingwen. Emotion Distribution Learning with Emotion Wheel Attention[J]. Computer Engineering and Applications, 2023, 59(4): 120-129.

参考文献

[1] ZHANG L，WANG S，LIU B.Deep learning for sentiment analysis：a survey[J].Wiley Interdisciplinary Reviews Data Mining & Knowledge Discovery，2018，8（4）：e1253.
[2] 赵妍妍，秦兵，刘挺.文本情感分析[J].软件学报，2010，21（8）：1834-1848.
ZHAO Y Y，QIN B，LIU T.Sentiment analysis[J].Journal of Software，2010，21（8）：1834-1848.
[3] SARASWAT M，CHAKRAVERTY S，KALA A.Analyzing emotion based movie recommender system using fuzzy emotion features[J].International Journal of Information Technology，2020，12（2）：467-472.
[4] 宋双永，王超，陈成龙，等.面向智能客服系统的情感分析技术[J].中文信息学报，2020，34（2）：80-95.
SONG S Y，WANG C，CHEN C L，et al.Sentiment analysis for intelligent customer service chatbots[J].Journal of Chinese Information Processing，2020，34（2）：80-95.
[5] XIN G.Label distribution learning[J].IEEE Transactions on Knowledge and Data Engineering，2016，28（7）：1734-1748.
[6] ZHOU Y，XUE H，GENG X.Emotion distribution recognition from facial expressions[C]//Proceedings of the 23rd ACM International Conference on Multimedia，2015：1247-1250.
[7] 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（1）：72-79.
ZENG X Q，LUO M Z，CHEN S F，et al.The facial age estimation based on adaptive multivariate multiple regression[J].Journal of Jiangxi Normal University（Natural Science Edition），2019，43（1）：72-79.
[8] STRAPPARAVA C，MIHALCEA R.SemEval-2007 task 14：affective text[C]//Proceedings of the 4th International Workshop on Semantic Evaluations，2007：70-74.
[9] XU Z，WANG S，WANG C.Exploiting multi-emotion relations at feature and label levels for emotion tagging[C]//Proceedings of the 28th ACM International Conference on Multimedia，2020：2955-2963.
[10] JIA X，ZHENG X，LI W，et al.Facial emotion distribution learning by exploiting low-rank label correlations locally[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：9833-9842.
[11] XU Z，WANG S.Emotional attention detection and correlation exploration for image emotion distribution learning[J].IEEE Transactions on Affective Computing，2021.DOI：10.1109/TAFFC.2021.3071131.
[12] HE T，JIN X.Image emotion distribution learning with graph convolutional networks[C]//Proceedings of the 2019 on International Conference on Multimedia Retrieval，2019：382-390.
[13] ZHOU D，ZHANG X，ZHOU Y，et al.Emotion distribution learning from texts[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing，2016：638-647.
[14] FEI H，ZHANG Y，REN Y，et al.Latent emotion memory for multi-label emotion classification[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence，the 32nd Innovative Applications of Artificial Intelligence Conference，the 10th AAAI Symposium on Educational Advances in Artificial Intelligence，2020：7692-7699.
[15] PLUTCHIK R.A general psychoevolutionary theory of emotion[J].Emotion Theory Research & Experience，2000，21（4/5）：529-553.
[16] SHAHRAKI A G.Emotion mining from text[D].University of Alberta，2015.
[17] SCHERER K R，WALLBOTT H G.Evidence for universality and cultural variation of differential emotion response patterning[J].Journal of Personality & Social Psychology，1994，66（2）：310-328.
[18] MOHAMMAD S.Emotional Tweets[C]//Proceedings of the 1st Joint Conference on Lexical and Computational，2012：246-255.
[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，2005：668-674.
[20] 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（5）：83-91.
YAO Y L，WANG S W，XU R F，et al.The construction of an emotion annotated corpus on microblog text[J].Journal of Chinese Information Processing，2014，28（5）：83-91.
[21] LI M，LONG Y，QIN L，et al.Emotion corpus construction based on selection from hashtags[C]//Proceedings of the 10th International Conference on Language Resources and Evaluation，2016：1845-1849.
[22] 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，2018：4595-4601.
[23] LI Z，XIE H，CHENG G，et al.Word-level emotion distribution with two schemas for short text emotion classification[J].Knowledge-Based Systems，2021，227：107163.
[24] MNIH V，HEESS N，GRAVES A，et al.Recurrent models of visual attention[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems，2014：2204-2212.
[25] BAHDANAU D，CHO K，BENGIO Y.Neural machine translation by jointly learning to align and translate[J].arXiv：1409.0473，2014.
[26] GENG X，YIN C，ZHOU Z H.Facial age estimation by learning from label distributions[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2013，35（10）：2401-2412.
[27] XU N，LIU Y，GENG X.Label enhancement for label distribution learning[J].IEEE Transactions on Knowledge & Data Engineering，2021，33（4）：1632-1643.
[28] MIKOLOV T，SUTSKEVER I，CHEN K，et al.Distributed representations of words and phrases and their compositionality[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems，2013：3111-3119.
[29] LI S，ZHAO Z，HU R，et al.Analogical reasoning on Chinese morphological and semantic relations[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics，2018：138-143.
[30] KIM Y.Convolutional neural networks for sentence classification[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing，2014：1746-1751.
[31] 曾雪强，华鑫，刘平生，等.基于情感轮和情感词典的文本情感分布标记增强方法[J].计算机学报，2021，44（6）：1080-1094.
ZENG X Q，HUA X，LIU P S，et al.Emotion wheel and lexicon based text emotion distribution label enhancement method[J].Chinese Journal of Computers，2021，44（6）：1080-1094.