Depression symptoms modelling from social media text: an LLM driven semi-supervised learning approach.

A fundamental component of user-level social media language based clinical depression modelling is depression symptoms detection (DSD). Unfortunately, there does not exist any DSD dataset that reflects both the clinical insights and the distribution of depression symptoms from the samples of self-di...

Descripción completa

Detalles Bibliográficos
Publicado en:Language Resources & Evaluation Vol. 58; no. 3; pp. 1013 - 1042
Autores principales: Farruque, Nawshad, Goebel, Randy, Sivapalan, Sudhakar, Zaïane, Osmar R.
Formato: Artículo
Publicado: Springer Nature Sep2024
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=179813864&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 179813864
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        1574020X
        179V
      jtl: Language Resources & Evaluation
      issn: 1574020X
      maglogo: N
    pubinfo:
      dt: Sep2024
      vid: 58
      iid: 3
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        179813864
        10.1007/s10579-024-09720-4
      ppf: 1013
      ppct: 29
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 1.3MB
      tig:
        atl: Depression symptoms modelling from social media text: an LLM driven semi-supervised learning approach.
      aug:
        au:
          Farruque, Nawshad
          Goebel, Randy
          Sivapalan, Sudhakar
          Zaïane, Osmar R.
        affil:
          https://ror.org/0160cpw27 Department of Computing Science, Faculty of Science, Alberta Machine Intelligence Institute (AMII), University of Alberta, T6G 2E8, Edmonton, AB, Canada
          https://ror.org/0160cpw27 Department of Psychiatry, Faculty of Medicine and Dentistry, University of Alberta, T6G 2H5, Edmonton, AB, Canada
      su:
        Language models
        Supervised learning
        Mental depression
        Social media
      sug:
        subj:
          Language models
          Supervised learning
          Mental depression
          Social media
      keyword:
        Bidirectional Encoder Representations from Transformers (BERT)
        Depression detection
        Depression symptoms detection
        Mental-BERT
        Semi-supervised learning
        Zero-shot learning
      ab: A fundamental component of user-level social media language based clinical depression modelling is depression symptoms detection (DSD). Unfortunately, there does not exist any DSD dataset that reflects both the clinical insights and the distribution of depression symptoms from the samples of self-disclosed depressed population. In our work, we describe a semi-supervised learning (SSL) framework which uses an initial supervised learning model that leverages (1) a state-of-the-art large mental health forum text pre-trained language model further fine-tuned on a clinician annotated DSD dataset, (2) a Zero-Shot learning model for DSD, and couples them together to harvest depression symptoms related samples from our large self-curated depressive tweets repository (DTR). Our clinician annotated dataset is the largest of its kind. Furthermore, DTR is created from the samples of tweets in self-disclosed depressed users Twitter timeline from two datasets, including one of the largest benchmark datasets for user-level depression detection from Twitter. This further helps preserve the depression symptoms distribution of self-disclosed tweets. Subsequently, we iteratively retrain our initial DSD model with the harvested data. We discuss the stopping criteria and limitations of this SSL process, and elaborate the underlying constructs which play a vital role in the overall SSL process. We show that we can produce a final dataset which is the largest of its kind. Furthermore, a DSD and a Depression Post Detection model trained on it achieves significantly better accuracy than their initial version.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Language Resources & Evaluation is a copyright of Springer, 2024. All Rights Reserved.
      item: Language Resources & Evaluation
      holder: Springer Nature
      dt:
        @attributes:
          year: 2024
    holdings:
      @attributes:
        islocal: N