View in EDS HTML Full Text PDF Full Text

Can an Algorithm Tell How Spiritual You Are? Using Generative Pretrained Transformers for Sophisticated Forms of Text Analysis.

Saved in:
Bibliographic Details
Title: Can an Algorithm Tell How Spiritual You Are? Using Generative Pretrained Transformers for Sophisticated Forms of Text Analysis.
Authors: Prinzing, Michael (AUTHOR), Bounds, Elizabeth (AUTHOR), Melton, Karen (AUTHOR), Glanzer, Perry (AUTHOR), Fredrickson, Barbara (AUTHOR), Schnitker, Sarah (AUTHOR)
Source: Journal of Personality. Dec2025, Vol. 93 Issue 6, p1258-1270. 13p.
Subjects: Spirituality, Generative pre-trained transformers, Research assistants, Content analysis, Narratives, Algorithms, Empirical research, Behavioral sciences
Abstract: Objective: Text analysis is a form of psychological assessment that involves converting qualitative information (text) into quantitative data. We tested whether automated text analysis using Generative Pre‐trained Transformers (GPTs) can match the "gold standard" of manual text analysis, even when assessing a highly nuanced construct like spirituality. Method: In Study 1, N = 2199 US undergraduates wrote about their goals (N = 6597 texts) and completed self‐reports of spirituality and theoretically related constructs (religiousness and mental health). In Study 2, N = 357 community adults wrote short essays (N = 714 texts) and completed trait self‐reports, 5 weeks of daily diaries, and behavioral measures of spirituality. Trained research assistants and GPTs then coded the texts for spirituality. Results: The GPTs performed just as well as human raters. Human‐ and GPT‐generated scores were remarkably consistent and showed equivalent associations with other measures of spirituality and theoretically related constructs. Conclusions: GPTs can match the gold standard set by human raters, even in sophisticated forms of text analysis, but require a fraction of the time and labor. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Personality is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Psychology and Behavioral Sciences Collection
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: pbh
DbLabel: Psychology and Behavioral Sciences Collection
An: 189189478
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Can an Algorithm Tell How Spiritual You Are? Using Generative Pretrained Transformers for Sophisticated Forms of Text Analysis.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Prinzing%2C+Michael%22">Prinzing, Michael</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Bounds%2C+Elizabeth%22">Bounds, Elizabeth</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Melton%2C+Karen%22">Melton, Karen</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Glanzer%2C+Perry%22">Glanzer, Perry</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Fredrickson%2C+Barbara%22">Fredrickson, Barbara</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Schnitker%2C+Sarah%22">Schnitker, Sarah</searchLink> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Personality%22">Journal of Personality</searchLink>. Dec2025, Vol. 93 Issue 6, p1258-1270. 13p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Spirituality%22">Spirituality</searchLink><br /><searchLink fieldCode="DE" term="%22Generative+pre-trained+transformers%22">Generative pre-trained transformers</searchLink><br /><searchLink fieldCode="DE" term="%22Research+assistants%22">Research assistants</searchLink><br /><searchLink fieldCode="DE" term="%22Content+analysis%22">Content analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Narratives%22">Narratives</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithms%22">Algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Empirical+research%22">Empirical research</searchLink><br /><searchLink fieldCode="DE" term="%22Behavioral+sciences%22">Behavioral sciences</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Objective: Text analysis is a form of psychological assessment that involves converting qualitative information (text) into quantitative data. We tested whether automated text analysis using Generative Pre‐trained Transformers (GPTs) can match the "gold standard" of manual text analysis, even when assessing a highly nuanced construct like spirituality. Method: In Study 1, N = 2199 US undergraduates wrote about their goals (N = 6597 texts) and completed self‐reports of spirituality and theoretically related constructs (religiousness and mental health). In Study 2, N = 357 community adults wrote short essays (N = 714 texts) and completed trait self‐reports, 5 weeks of daily diaries, and behavioral measures of spirituality. Trained research assistants and GPTs then coded the texts for spirituality. Results: The GPTs performed just as well as human raters. Human‐ and GPT‐generated scores were remarkably consistent and showed equivalent associations with other measures of spirituality and theoretically related constructs. Conclusions: GPTs can match the gold standard set by human raters, even in sophisticated forms of text analysis, but require a fraction of the time and labor. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Personality is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=pbh&AN=189189478
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1111/jopy.13006
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 1258
    Subjects:
      – SubjectFull: Spirituality
        Type: general
      – SubjectFull: Generative pre-trained transformers
        Type: general
      – SubjectFull: Research assistants
        Type: general
      – SubjectFull: Content analysis
        Type: general
      – SubjectFull: Narratives
        Type: general
      – SubjectFull: Algorithms
        Type: general
      – SubjectFull: Empirical research
        Type: general
      – SubjectFull: Behavioral sciences
        Type: general
    Titles:
      – TitleFull: Can an Algorithm Tell How Spiritual You Are? Using Generative Pretrained Transformers for Sophisticated Forms of Text Analysis.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Prinzing, Michael
      – PersonEntity:
          Name:
            NameFull: Bounds, Elizabeth
      – PersonEntity:
          Name:
            NameFull: Melton, Karen
      – PersonEntity:
          Name:
            NameFull: Glanzer, Perry
      – PersonEntity:
          Name:
            NameFull: Fredrickson, Barbara
      – PersonEntity:
          Name:
            NameFull: Schnitker, Sarah
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Text: Dec2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 00223506
          Numbering:
            – Type: volume
              Value: 93
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Journal of Personality
              Type: main
ResultId 1