Assessing environmental determinants of subjective well-being via machine learning approaches: a systematic review.

Understanding the determinants of subjective well-being (SWB) is crucial for advancing social sciences, particularly in relation to environmental and social factors. Machine learning (ML) techniques have gained popularity in SWB research, yet there is limited synthesis of their current implementatio...

Descripción completa

Detalles Bibliográficos
Publicado en:Humanities & Social Sciences Communications Vol. 12; no. 1; pp. 1 - 16
Autores principales: Yang, Min, Zou, Yuxuan
Formato: Artículo
Publicado: Springer Nature 6/17/2025
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=185966904&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 185966904
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid: MVR0
      jtl: Humanities & Social Sciences Communications
      maglogo: N
    pubinfo:
      dt: 6/17/2025
      vid: 12
      iid: 1
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        185966904
        10.1057/s41599-025-05234-8
      ppf: 1
      ppct: 15
      formats:
      tig:
        atl: Assessing environmental determinants of subjective well-being via machine learning approaches: a systematic review.
      aug:
        au:
          Yang, Min
          Zou, Yuxuan
        affil:
          https://ror.org/0030zas98 Hong Kong Polytechnic University, Hong Kong, China
          https://ror.org/0145fw131 Hong Kong Baptist University, Hong Kong, China
      su:
        Artificial neural networks
        Subjective well-being (Psychology)
        Random forest algorithms
        Social factors
        Well-being
      sug:
        subj:
          Artificial neural networks
          Subjective well-being (Psychology)
          Random forest algorithms
          Social factors
          Well-being
      ab: Understanding the determinants of subjective well-being (SWB) is crucial for advancing social sciences, particularly in relation to environmental and social factors. Machine learning (ML) techniques have gained popularity in SWB research, yet there is limited synthesis of their current implementation. This systematic review examines the application of ML techniques in assessing determinants of SWB, providing a comprehensive synthesis of 25 studies published up to March 2024. The review highlights the growing use of ML methods, such as random forests, artificial neural networks, and gradient boosting, in understanding the complex, non-linear relationships between environmental factors and SWB. Key environmental determinants identified include service accessibility such as parks, supermarkets, and hospitals, safety feelings, and exposure to air pollution. Additionally, significant social factors, including sociodemographics, emotional predictors, family predictors, and social capital, also influence SWB. The review underscores the value of ML in revealing non-linear relationships and threshold effects, which are particularly useful for policymakers aiming to optimize interventions to enhance public well-being. Analysis of the importance of variables within these models enables policymakers to prioritize interventions that target the most influential factors. However, the review also identifies challenges in the application of ML, particularly in model reporting, improved interpretability techniques, and methodological rigor. These insights provide a foundation for future research aiming to leverage ML to generate more robust and actionable knowledge in well-being studies. To fully harness the potential of ML in SWB research and prevent its misuse, future studies should prioritize model interpretability and focus on translating these insights into actionable policy recommendations.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2025
    holdings:
      @attributes:
        islocal: N