Using topic modeling to infer the emotional state of people living with Parkinson's disease.

Individuals with Parkinson's disease (PD) often exhibit facial masking (hypomimia), which causes reduced facial expressiveness. This can make it difficult for those who interact with the person to correctly read their emotional state and can lead to problematic social and therapeutic interactions. In...

Descripción completa

Detalles Bibliográficos
Publicado en:Assistive Technology Vol. 33; no. 3; pp. 136 - 146
Autores principales: Valenti MS, Andrew P., Chita-Tegmark PhD, Meia, Tickle-Degnen PhD, OTR/L, FAOTA, Linda, Bock BS, Alexander W., Scheutz PhD, Matthias J.
Formato: equations & formulas research tables/charts Journal Article
Publicado: Taylor & Francis Ltd 2021
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=151680186&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 151680186
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        10400435
        YVP
      jtl: Assistive Technology
      issn: 10400435
      maglogo: Y
    pubinfo:
      dt: 2021
      vid: 33
      iid: 3
      pid: 377
      pub: Taylor & Francis Ltd
      place: Philadelphia, Pennsylvania
    artinfo:
      ui:
        151680186
        151680186
        151680186
        10.1080/10400435.2019.1623342
        151680186
      ppf: 136
      ppct: 10
      formats:
        fmt:
          @attributes:
            type: P
      tig:
        atl: Using topic modeling to infer the emotional state of people living with Parkinson's disease.
      aug:
        au:
          Valenti MS, Andrew P.
          Chita-Tegmark PhD, Meia
          Tickle-Degnen PhD, OTR/L, FAOTA, Linda
          Bock BS, Alexander W.
          Scheutz PhD, Matthias J.
        affil: Tufts University Human-Robot Interaction Laboratory, Medford, Massachusetts, USA
      sug:
        subj:
          Models, Statistical
          Emotions Evaluation
          Parkinson Disease Psychosocial Factors
          Professional-Patient Relations
          Human
          Assistive Technology Devices
          Caregivers
          Facial Expression
          Biofeedback
          Word Lists
          Interviews
          Predictive Value of Tests
          Funding Source
          Male
          Female
          Aged
          Data Management
          Machine Learning
          Analysis of Variance
          Software
          Logistic Regression
          Probability
          Aged: 65+ years
          Male
          Female
      ab: Individuals with Parkinson's disease (PD) often exhibit facial masking (hypomimia), which causes reduced facial expressiveness. This can make it difficult for those who interact with the person to correctly read their emotional state and can lead to problematic social and therapeutic interactions. In this article, we develop a probabilistic model for an assistive device, which can automatically infer the emotional state of a person with PD using the topics that arise during the course of a conversation. We envision that the model can be situated in a device that could monitor the emotional content of the interaction between the caregiver and a person living with PD, providing feedback to the caregiver in order to correct their immediate and perhaps incorrect impressions arising from a reliance on facial expressions. We compare and contrast two approaches: using the Latent Dirichlet Allocation (LDA) generative model as the basis for an unsupervised learning tool, and using a human-crafted sentiment analysis tool, the Linguistic Inquiry and Word Count (LIWC). We evaluated both approaches using standard machine learning performance metrics such as precision, recall, and F 1 scores. Our performance analysis of the two approaches suggests that LDA is a suitable classifier when the word count in a document is approximately that of the average sentence, i.e., 13 words. In that case, the LDA model correctly predicts the interview category 86% of the time and LIWC correctly predicts it 29% of the time. On the other hand, when tested with interviews with an average word count of 303 words, the LDA model correctly predicts the interview category 56% of the time and LIWC, 74% of the time. Advantages and disadvantages of the two approaches are discussed.
      pubtype: Academic Journal
      doctype:
        equations & formulas
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N