Detecting defense mechanisms from Adult Attachment Interview (AAI) transcripts using machine learning.

Defensive functioning (i.e., unconscious process used to manage real or perceived threats) may play a role in the development of various psychopathologies. It is typically assessed via observer rating measures, however, human coding of defensive functioning is resource-intensive and time-consuming....

Full description

Bibliographic Details
Published in:Psychotherapy Research Vol. 33; no. 6; pp. 757 - 768
Main Authors: Tasca, Anthony N., Carlucci, Samantha, Wiley, James C., Holden, Matthew, El-Roby, Ahmed, Tasca, Giorgio A.
Format: Article
Published: Taylor & Francis Ltd Jul2023
Subjects:
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=164439877&site=ehost-live
header:
  @attributes:
    shortDbName: ssf
    uiTerm: 164439877
    longDbName: Social Sciences Full Text (H.W. Wilson)
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        10503307
        10T
      jtl: Psychotherapy Research
      issn: 10503307
      maglogo: N
    pubinfo:
      dt: Jul2023
      vid: 33
      iid: 6
      pid: 377
      pub: Taylor & Francis Ltd
    artinfo:
      ui:
        164439877
        10.1080/10503307.2022.2156306
      ppf: 757
      ppct: 11
      formats:
      tig:
        atl: Detecting defense mechanisms from Adult Attachment Interview (AAI) transcripts using machine learning.
      aug:
        au:
          Tasca, Anthony N.
          Carlucci, Samantha
          Wiley, James C.
          Holden, Matthew
          El-Roby, Ahmed
          Tasca, Giorgio A.
        affil:
          School of Computer Science, Carleton University, Ottawa, Canada
          School of Psychology, University of Ottawa, Ottawa, Canada
          Clinical Epidemiology Program, Ottawa Hospital Research Institute, Ottawa, Canada
          Department of Psychology, Carleton University, Ottawa, Canada
      su:
        Binge-eating disorder
        Adults
        Communities
        Machine learning
      sug:
        subj:
          Binge-eating disorder
          Adults
          Communities
          Machine learning
      keyword:
        conversation analysis
        Defense Mechanism Rating Scale
        defensive functioning
        machine learning
        RoBERTa
        conversation analysis
        Defense Mechanism Rating Scale
        defensive functioning
        machine learning
        RoBERTa
      ab: Defensive functioning (i.e., unconscious process used to manage real or perceived threats) may play a role in the development of various psychopathologies. It is typically assessed via observer rating measures, however, human coding of defensive functioning is resource-intensive and time-consuming. The purpose of this study was to develop a machine learning approach to automate coding of defense mechanisms from interview transcripts. Participants included a clinical sample of women with binge-eating disorder (n = 92) and a community sample without binge-eating disorder (n = 66). We trained and evaluated five RoBERTa-based models to detect the presence of defenses in 16,785 interviewer-participant talk-turn pairs nested within 192 interviews. A model detected the presence of any defense, while four additional models detected the most common defenses in this sample (repression, intellectualization, reaction formation, undoing). The models were capable of distinguishing defenses (ROC-AUC.82-.90) but were not proficient enough to warrant replacing human coders (PR-AUC.28-.60). Follow-up analysis was performed to assess other practical uses of these models. Our machine learning models could be used to assist coders. Future research should conduct a deployment study to determine if human coding of defense mechanisms can be expedited using machine learning models.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: N
    holdings:
      @attributes:
        islocal: N