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...

Full description

Bibliographic Details
Published in:Language Resources & Evaluation Vol. 59; no. 4; pp. 3975 - 4003
Main Authors: Odbal, Zheng, Zhong, Zhang, Guanhong
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