Data-driven weakly supervised emotion classification with consistency regularization: Mandarin Chinese as a case.
Emotion classification from text is a crucial task in affective computing, with applications in social informatics, human-computer interaction, and urban data analysis. This task involves identifying emotional states and answering questions such as, "Is the writer or reader happy, angry, or fearful...
| Published in: | Language Resources & Evaluation Vol. 59; no. 4; pp. 3975 - 4003 |
|---|---|
| Main Authors: | , , |
| Format: | Article |
| Published: |
Springer Nature
Dec2025
|
| Subjects: | |
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=189912040&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 189912040 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 1574020X 179V jtl: Language Resources & Evaluation issn: 1574020X maglogo: N pubinfo: dt: Dec2025 vid: 59 iid: 4 pid: 237 pub: Springer Nature artinfo: ui: 189912040 10.1007/s10579-025-09868-7 ppf: 3975 ppct: 28 formats: fmt: – @attributes: type: T – @attributes: type: P size: 2.2MB tig: atl: Data-driven weakly supervised emotion classification with consistency regularization: Mandarin Chinese as a case. aug: au: Odbal Zheng, Zhong Zhang, Guanhong affil: https://ror.org/03myvh511 Anhui Vocational and Technical College, Hefei, China https://ror.org/046n57345 Hefei Institute of Physical Sciences, Chinese Academy of Sciences, Hefei, China https://ror.org/01f5rdf64 Hefei University, Hefei, China su: Emotion recognition Affective computing Machine learning Content analysis Supervised learning Artificial neural networks Mandarin dialects sug: subj: Emotion recognition Affective computing Machine learning Content analysis Supervised learning Artificial neural networks Mandarin dialects keyword: Compact neighbor consistency regularization Data-driven emotion classification Heuristic rules Information and Computing Sciences Artificial Intelligence and Image Processing Information Systems Transformer architectures Weakly-supervised learning ab: Emotion classification from text is a crucial task in affective computing, with applications in social informatics, human-computer interaction, and urban data analysis. This task involves identifying emotional states and answering questions such as, "Is the writer or reader happy, angry, or fearful about the target?" While deep neural network (DNN)-based models are effective at this task, they frequently require large labelled datasets, which are expensive and impractical, especially for dynamic, irregular data seen on platforms such as social media. To address these challenges, an efficient weakly-supervised learning framework is proposed for text emotion classification that reduces reliance on large-scale annotations. A Transformer-based model and anchor-based similarity computations are incorporated within a self-training framework to generate weakly labeled data. A compact neighbor consistency regularization (CNCR) mechanism is introduced to improve classification robustness across diverse datasets. Additionally, heuristic rules are designed to filter raw data, manage noise, and ensure better model generalization across different datasets. Extensive experiments were conducted on three real-world datasets, demonstrating that the proposed method is both efficient and comparable to previous semi-supervised learning algorithms. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Language Resources & Evaluation is a copyright of Springer, 2025. All Rights Reserved. item: Language Resources & Evaluation holder: Springer Nature dt: @attributes: year: 2025 holdings: @attributes: islocal: N |
|---|