Multi-source domain adaptation method for textual emotion classification using deep and broad learning

doi:10.1016/j.knosys.2022.110173

	Multi-source domain adaptation method for textual emotion classification using deep and broad learning
	Peng, Sancheng 1; Zeng, Rong 2; Cao, Lihong 1; Yang, Aimin 3; Niu, Jianwei 4; Zong, Chengqing5 ; Zhou, Guodong 6
发表期刊	KNOWLEDGE-BASED SYSTEMS
ISSN	0950-7051
	2023-01-25
卷号	260 页码:9
通讯作者	Cao, Lihong(201610130@oamail.gdufs.edu.cn)
摘要	Existing domain adaptation methods for classifying textual emotions have the propensity to focus on single-source domain exploration rather than multi-source domain adaptation. The efficacy of emotion classification is hampered by the restricted information and volume from a single source domain. Thus, to improve the performance of domain adaptation, we present a novel multi-source domain adaptation approach for emotion classification, by combining broad learning and deep learning in this article. Specifically, we first design a model to extract domain-invariant features from each source domain to the same target domain by using BERT and Bi-LSTM, which can better capture contextual features. Then we adopt broad learning to train multiple classifiers based on the domain-invariant features, which can more effectively conduct multi-label classification tasks. In addition, we design a co-training model to boost these classifiers. Finally, we carry out several experiments on four datasets by comparison with the baseline methods. The experimental results show that our proposed approach can significantly outperform the baseline methods for textual emotion classification.(c) 2022 Published by Elsevier B.V.
关键词	Multi-domain Emotion classification BERT Broad learning Bi-LSTM
DOI	10.1016/j.knosys.2022.110173
收录类别	SCI
语种	英语
资助项目	National Natural Sci- ence Foundation of China ; Ministry of Education of Humanities and Social Science project ; [61876205] ; [20YJAZH118]
项目资助者	National Natural Sci- ence Foundation of China ; Ministry of Education of Humanities and Social Science project
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000905783200001
出版者	ELSEVIER
引用统计	被引频次：3[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/173211/51109
专题	复杂系统认知与决策实验室
通讯作者	Cao, Lihong
作者单位	1.Guangdong Univ Foreign Studies, Lab Language Engn & Comp, Guangzhou 510006, Peoples R China 2.South China Normal Univ, Guangdong Prov Key Lab Nanophoton Funct Mat & Devi, Guangzhou 510006, Peoples R China 3.Lingnan Normal Univ, Sch Comp Sci & Intelligence Educ, Zhanjiang 524048, Peoples R China 4.Beihang Univ, State Key Lab Virtual Real Technol & Syst, Beijing 100191, Peoples R China 5.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 6.Soochow Univ, Sch Comp Sci & Technol, Suzhou, Peoples R China
推荐引用方式 GB/T 7714	Peng, Sancheng,Zeng, Rong,Cao, Lihong,et al. Multi-source domain adaptation method for textual emotion classification using deep and broad learning[J]. KNOWLEDGE-BASED SYSTEMS,2023,260:9.
APA	Peng, Sancheng.,Zeng, Rong.,Cao, Lihong.,Yang, Aimin.,Niu, Jianwei.,...&Zhou, Guodong.(2023).Multi-source domain adaptation method for textual emotion classification using deep and broad learning.KNOWLEDGE-BASED SYSTEMS,260,9.
MLA	Peng, Sancheng,et al."Multi-source domain adaptation method for textual emotion classification using deep and broad learning".KNOWLEDGE-BASED SYSTEMS 260(2023):9.