Assessing environmental determinants of subjective well-being via machine learning approaches: a systematic review
Abstract 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 impl...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer Nature
2025-06-01
|
| Series: | Humanities & Social Sciences Communications |
| Online Access: | https://doi.org/10.1057/s41599-025-05234-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850207429745180672 |
|---|---|
| author | Min Yang Yuxuan Zou |
| author_facet | Min Yang Yuxuan Zou |
| author_sort | Min Yang |
| collection | DOAJ |
| description | Abstract 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. |
| format | Article |
| id | doaj-art-7e4d47cf4abe4170ac37b172bf1a778f |
| institution | OA Journals |
| issn | 2662-9992 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Springer Nature |
| record_format | Article |
| series | Humanities & Social Sciences Communications |
| spelling | doaj-art-7e4d47cf4abe4170ac37b172bf1a778f2025-08-20T02:10:31ZengSpringer NatureHumanities & Social Sciences Communications2662-99922025-06-0112111510.1057/s41599-025-05234-8Assessing environmental determinants of subjective well-being via machine learning approaches: a systematic reviewMin Yang0Yuxuan Zou1Hong Kong Polytechnic UniversityHong Kong Baptist UniversityAbstract 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.https://doi.org/10.1057/s41599-025-05234-8 |
| spellingShingle | Min Yang Yuxuan Zou Assessing environmental determinants of subjective well-being via machine learning approaches: a systematic review Humanities & Social Sciences Communications |
| title | Assessing environmental determinants of subjective well-being via machine learning approaches: a systematic review |
| title_full | Assessing environmental determinants of subjective well-being via machine learning approaches: a systematic review |
| title_fullStr | Assessing environmental determinants of subjective well-being via machine learning approaches: a systematic review |
| title_full_unstemmed | Assessing environmental determinants of subjective well-being via machine learning approaches: a systematic review |
| title_short | Assessing environmental determinants of subjective well-being via machine learning approaches: a systematic review |
| title_sort | assessing environmental determinants of subjective well being via machine learning approaches a systematic review |
| url | https://doi.org/10.1057/s41599-025-05234-8 |
| work_keys_str_mv | AT minyang assessingenvironmentaldeterminantsofsubjectivewellbeingviamachinelearningapproachesasystematicreview AT yuxuanzou assessingenvironmentaldeterminantsofsubjectivewellbeingviamachinelearningapproachesasystematicreview |