Emotion Label Enhancement via Emotion Wheel and Lexicon

Emotion Label Enhancement via Emotion Wheel and Lexicon
复制标题

通过情感轮和词典增强情感标签

DOI:
10.1155/2021/6695913
复制
发表时间:
2021-04
影响因子:
--
通讯作者:
Zuo Jiali
Zuo Jiali
中科院分区:
工程技术4区
文献类型:
--
作者:
Zeng Xueqiang;Chen Qifan;Chen Sufen;Zuo Jiali

文献摘要

参考文献

相似文献

情感分布学习是近年来提出的一种多情感分析范式,它识别句子中不同表达程度的基本情感。与传统方法不同的是,该模型定量地描述了情感分布中对应情感在给定实例上的表达程度。然而,在大多数现有的情感数据集中,情感标签是清晰的。标签增强的目的是将逻辑情感标签转换为情感分布,以利用传统的情感数据集。利用情感词的语言情感信息和Plutchik情感轮的心理学知识,提出了一种新的标签增强方法--情感轮和基于词典的情感分布标签增强(EWLLE)。EWLLE方法基于心理情感距离为句子的情感标签和情感词的情感标签分别生成离散的高斯分布,并通过分布叠加将两类信息组合成统一的情感分布。在4个常用的文本情感数据集上的实验表明,与现有的EDL标签增强方法相比,EWLLE方法在情感分类方面具有明显的优势.
Emotion Distribution Learning (EDL) is a recently proposed multiemotion analysis paradigm, which identifies basic emotions with different degrees of expression in a sentence. Different from traditional methods, EDL quantitatively models the expression degree of the corresponding emotion on the given instance in an emotion distribution. However, emotion labels are crisp in most existing emotion datasets. To utilize traditional emotion datasets in EDL, label enhancement aims to convert logical emotion labels into emotion distributions. This paper proposed a novel label enhancement method, called Emotion Wheel and Lexicon-based emotion distribution Label Enhancement (EWLLE), utilizing the affective words’ linguistic emotional information and the psychological knowledge of Plutchik’s emotion wheel. The EWLLE method generates separate discrete Gaussian distributions for the emotion label of sentence and the emotion labels of sentiment words based on the psychological emotion distance and combines the two types of information into a unified emotion distribution by superposition of the distributions. The extensive experiments on 4 commonly used text emotion datasets showed that the proposed EWLLE method has a distinct advantage over the existing EDL label enhancement methods in the emotion classification task.
DOI: 10.1016/j.eswa.2020.113683
发表时间: 2020-12
影响因子: 8.5
作者:
Xugang Xi;Yan Zhang;Xian Hua;Seyed M. Miran;Yun-Bo Zhao;Zhizeng Luo
通讯作者: Zhizeng Luo
DOI: 10.7544/issn1000-1239.2017.20170002
发表时间: 2017-06
期刊: Journal of Computer Research and Development
影响因子: --
作者:
Geng Xin;Ning Xu;Shao Ruifeng
通讯作者: Geng Xin;Ning Xu;Shao Ruifeng
DOI: 10.1109/tkde.2019.2951561
发表时间: 2019-11
影响因子: 8.9
作者:
Min-Ling Zhang;Qian-Wen Zhang;Jun-Peng Fang;Yukun Li;Xin Geng
通讯作者: Min-Ling Zhang;Qian-Wen Zhang;Jun-Peng Fang;Yukun Li;Xin Geng
DOI: 10.1145/3057270
发表时间: 2017-06-01
影响因子: 16.6
作者:
Yadollahi, Ali;Shahraki, Ameneh Gholipour;Zaiane, Osmar R.
通讯作者: Zaiane, Osmar R.
DOI: 10.18653/v1/d19-1408
发表时间: 2019-11
期刊: --
影响因子: --
作者:
Zhenjie Zhao;Xiaojuan Ma
通讯作者: Zhenjie Zhao;Xiaojuan Ma