Emotion Wheel Attention-Based Emotion Distribution Learning

Emotion distribution learning is an effective multi-emotion analysis model proposed in recent years. Its core idea is to record the expression degree of examples on each emotion through emotion distribution, which is suitable for handling emotion analysis tasks with emotional ambiguity. To solve the...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xueqiang Zeng, Qifan Chen, Xuefeng Fu, Jiali Zuo
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Emotion distribution learning emotion wheel attention mechanism emotion classification Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/73f71579424a4ab2b40473fee51e1c40
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:73f71579424a4ab2b40473fee51e1c40
record_format	dspace
spelling	oai:doaj.org-article:73f71579424a4ab2b40473fee51e1c402021-11-24T00:02:35ZEmotion Wheel Attention-Based Emotion Distribution Learning2169-353610.1109/ACCESS.2021.3119464https://doaj.org/article/73f71579424a4ab2b40473fee51e1c402021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9566841/https://doaj.org/toc/2169-3536Emotion distribution learning is an effective multi-emotion analysis model proposed in recent years. Its core idea is to record the expression degree of examples on each emotion through emotion distribution, which is suitable for handling emotion analysis tasks with emotional ambiguity. To solve the problem that the prior knowledge of emotion psychology is seldom considered in the existing emotion distribution learning methods, we propose an Emotion Wheel Attention based Emotion Distribution Learning (EWA-EDL) model. EWA-EDL generates a prior emotion distribution describing the relevance of emotional psychology for each basic emotion, and then directly integrates the prior knowledge based on the emotion wheel into the deep neural network through the attention mechanism. The deep network of EWA-EDL is trained using an end-to-end approach to learn both emotion distribution prediction and emotion classification tasks. The EWA-EDL architecture includes five main parts: input layer, convolutional layer, pooling layer, attention layer and multi-task loss layer. Extensive comparative experiments on 8 commonly used textual emotion datasets show that EWA-EDL outperforms the comparison emotion distribution learning methods on both emotion distribution prediction and emotion classification task.Xueqiang ZengQifan ChenXuefeng FuJiali ZuoIEEEarticleEmotion distribution learningemotion wheelattention mechanismemotion classificationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 153360-153370 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Emotion distribution learning emotion wheel attention mechanism emotion classification Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Emotion distribution learning emotion wheel attention mechanism emotion classification Electrical engineering. Electronics. Nuclear engineering TK1-9971 Xueqiang Zeng Qifan Chen Xuefeng Fu Jiali Zuo Emotion Wheel Attention-Based Emotion Distribution Learning
description	Emotion distribution learning is an effective multi-emotion analysis model proposed in recent years. Its core idea is to record the expression degree of examples on each emotion through emotion distribution, which is suitable for handling emotion analysis tasks with emotional ambiguity. To solve the problem that the prior knowledge of emotion psychology is seldom considered in the existing emotion distribution learning methods, we propose an Emotion Wheel Attention based Emotion Distribution Learning (EWA-EDL) model. EWA-EDL generates a prior emotion distribution describing the relevance of emotional psychology for each basic emotion, and then directly integrates the prior knowledge based on the emotion wheel into the deep neural network through the attention mechanism. The deep network of EWA-EDL is trained using an end-to-end approach to learn both emotion distribution prediction and emotion classification tasks. The EWA-EDL architecture includes five main parts: input layer, convolutional layer, pooling layer, attention layer and multi-task loss layer. Extensive comparative experiments on 8 commonly used textual emotion datasets show that EWA-EDL outperforms the comparison emotion distribution learning methods on both emotion distribution prediction and emotion classification task.
format	article
author	Xueqiang Zeng Qifan Chen Xuefeng Fu Jiali Zuo
author_facet	Xueqiang Zeng Qifan Chen Xuefeng Fu Jiali Zuo
author_sort	Xueqiang Zeng
title	Emotion Wheel Attention-Based Emotion Distribution Learning
title_short	Emotion Wheel Attention-Based Emotion Distribution Learning
title_full	Emotion Wheel Attention-Based Emotion Distribution Learning
title_fullStr	Emotion Wheel Attention-Based Emotion Distribution Learning
title_full_unstemmed	Emotion Wheel Attention-Based Emotion Distribution Learning
title_sort	emotion wheel attention-based emotion distribution learning
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/73f71579424a4ab2b40473fee51e1c40
work_keys_str_mv	AT xueqiangzeng emotionwheelattentionbasedemotiondistributionlearning AT qifanchen emotionwheelattentionbasedemotiondistributionlearning AT xuefengfu emotionwheelattentionbasedemotiondistributionlearning AT jializuo emotionwheelattentionbasedemotiondistributionlearning
_version_	1718416099703259136

Emotion Wheel Attention-Based Emotion Distribution Learning

Ejemplares similares