Automating psychological hypothesis generation with AI: when large language models meet causal graph.

Leveraging the synergy between causal knowledge graphs and a large language model (LLM), our study introduces a groundbreaking approach for computational hypothesis generation in psychology. We analyzed 43,312 psychology articles using a LLM to extract causal relation pairs. This analysis produced a...

Full description

Bibliographic Details
Published in:Humanities & Social Sciences Communications Vol. 11; no. 1; pp. 1 - 15
Main Authors: Tong, Song, Mao, Kai, Huang, Zhen, Zhao, Yukun, Peng, Kaiping
Format: Article
Published: Springer Nature 7/9/2024
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=178354343&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 178354343
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid: MVR0
      jtl: Humanities & Social Sciences Communications
      maglogo: N
    pubinfo:
      dt: 7/9/2024
      vid: 11
      iid: 1
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        178354343
        10.1057/s41599-024-03407-5
      ppf: 1
      ppct: 14
      formats:
      tig:
        atl: Automating psychological hypothesis generation with AI: when large language models meet causal graph.
      aug:
        au:
          Tong, Song
          Mao, Kai
          Huang, Zhen
          Zhao, Yukun
          Peng, Kaiping
        affil:
          https://ror.org/03cve4549 Department of Psychological and Cognitive Sciences, Tsinghua University, Beijing, China
          https://ror.org/03cve4549 Positive Psychology Research Center, School of Social Sciences, Tsinghua University, Beijing, China
          https://ror.org/03cve4549 AI for Wellbeing Lab, Tsinghua University, Beijing, China
          https://ror.org/03cve4549 Institute for Global Industry, Tsinghua University, Beijing, China
          Kindom KK, Tokyo, Japan
      su:
        Language models
        Causal models
        Knowledge graphs
        Artificial intelligence
        Machine learning
        Well-being
      sug:
        subj:
          Language models
          Causal models
          Knowledge graphs
          Artificial intelligence
          Machine learning
          Well-being
      ab: Leveraging the synergy between causal knowledge graphs and a large language model (LLM), our study introduces a groundbreaking approach for computational hypothesis generation in psychology. We analyzed 43,312 psychology articles using a LLM to extract causal relation pairs. This analysis produced a specialized causal graph for psychology. Applying link prediction algorithms, we generated 130 potential psychological hypotheses focusing on "well-being", then compared them against research ideas conceived by doctoral scholars and those produced solely by the LLM. Interestingly, our combined approach of a LLM and causal graphs mirrored the expert-level insights in terms of novelty, clearly surpassing the LLM-only hypotheses (t(59) = 3.34, p = 0.007 and t(59) = 4.32, p < 0.001, respectively). This alignment was further corroborated using deep semantic analysis. Our results show that combining LLM with machine learning techniques such as causal knowledge graphs can revolutionize automated discovery in psychology, extracting novel insights from the extensive literature. This work stands at the crossroads of psychology and artificial intelligence, championing a new enriched paradigm for data-driven hypothesis generation in psychological research.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2024
    holdings:
      @attributes:
        islocal: N