CNN-Based Broad Learning for Cross-Domain Emotion Classification

doi:10.26599/TST.2022.9010007

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 自然语言处理

	CNN-Based Broad Learning for Cross-Domain Emotion Classification
	Zeng, Rong 1; Liu, Hongzhan 1; Peng, Sancheng 2; Cao, Lihong 2; Yang, Aimin 3; Zong, Chengqing4 ; Zhou, Guodong 5
发表期刊	TSINGHUA SCIENCE AND TECHNOLOGY
ISSN	1007-0214
	2023-04-01
卷号	28 期号:2 页码:360-369
通讯作者	Liu, Hongzhan(lhzscnu@163.com) ; Peng, Sancheng(psc346@aliyun.com)
摘要	Cross-domain emotion classification aims to leverage useful information in a source domain to help predict emotion polarity in a target domain in a unsupervised or semi-supervised manner. Due to the domain discrepancy, an emotion classifier trained on source domain may not work well on target domain. Many researchers have focused on traditional cross-domain sentiment classification, which is coarse-grained emotion classification. However, the problem of emotion classification for cross-domain is rarely involved. In this paper, we propose a method, called convolutional neural network (CNN) based broad learning, for cross-domain emotion classification by combining the strength of CNN and broad learning. We first utilized CNN to extract domain-invariant and domain-specific features simultaneously, so as to train two more efficient classifiers by employing broad learning. Then, to take advantage of these two classifiers, we designed a co-training model to boost together for them. Finally, we conducted comparative experiments on four datasets for verifying the effectiveness of our proposed method. The experimental results show that the proposed method can improve the performance of emotion classification more effectively than those baseline methods.
关键词	Measurement Deep learning Adaptation models Feature extraction Convolutional neural networks Data mining Task analysis cross-domain emotion classification CNN broad learning classifier co-training
DOI	10.26599/TST.2022.9010007
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Engineering, Electrical & Electronic
WOS记录号	WOS:000862392800014
出版者	TSINGHUA UNIV PRESS
引用统计	被引频次：8[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/50401
专题	多模态人工智能系统全国重点实验室_自然语言处理
通讯作者	Liu, Hongzhan; Peng, Sancheng
作者单位	1.South China Normal Univ, Guangdong Prov Key Lab Nanophoton Funct Mat & Dev, Guangzhou 511400, Peoples R China 2.Guangdong Univ Foreign Studies, Lab Language Engn & Comp, Guangzhou 510006, Peoples R China 3.Lingnan Normal Univ, Sch Comp Sci & Intelligence Educ, Guangzhou 510006, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 5.Soochow Univ, Sch Comp Sci & Technol, Suzhou 215031, Peoples R China
推荐引用方式 GB/T 7714	Zeng, Rong,Liu, Hongzhan,Peng, Sancheng,et al. CNN-Based Broad Learning for Cross-Domain Emotion Classification[J]. TSINGHUA SCIENCE AND TECHNOLOGY,2023,28(2):360-369.
APA	Zeng, Rong.,Liu, Hongzhan.,Peng, Sancheng.,Cao, Lihong.,Yang, Aimin.,...&Zhou, Guodong.(2023).CNN-Based Broad Learning for Cross-Domain Emotion Classification.TSINGHUA SCIENCE AND TECHNOLOGY,28(2),360-369.
MLA	Zeng, Rong,et al."CNN-Based Broad Learning for Cross-Domain Emotion Classification".TSINGHUA SCIENCE AND TECHNOLOGY 28.2(2023):360-369.