AI-assisted discovery of quantitative and formal models in social science
In social science, formal and quantitative models, ranging from ones that describe economic growth to collective action, are used to formulate mechanistic explanations of the observed phenomena, provide predictions, and uncover new research questions. Here, we demonstrate the use of a machine learni...
| Main Authors: | , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Springer Nature [academic journals on nature.com]
2025
|
| _version_ | 1824459112862187520 |
|---|---|
| author | Balla, J Huang, S Dugan, O Dangovski, R Soljačić, M |
| author_facet | Balla, J Huang, S Dugan, O Dangovski, R Soljačić, M |
| author_sort | Balla, J |
| collection | OXFORD |
| description | In social science, formal and quantitative models, ranging from ones that describe economic growth to collective action, are used to formulate mechanistic explanations of the observed phenomena, provide predictions, and uncover new research questions. Here, we demonstrate the use of a machine learning system to aid the discovery of symbolic models that capture non-linear and dynamical relationships in social science datasets. By extending neuro-symbolic methods to find compact functions and differential equations in noisy and longitudinal data, we show that our system can be used to discover interpretable models from real-world data in economics and sociology. Augmenting existing workflows with symbolic regression can help uncover novel relationships and explore counterfactual models during the scientific process. We propose that this AI-assisted framework can bridge parametric and non-parametric models commonly employed in social science research by systematically exploring the space of non-linear models and enabling fine-grained control over expressivity and interpretability. |
| first_indexed | 2025-02-19T04:36:37Z |
| format | Journal article |
| id | oxford-uuid:9e652c50-84b6-4352-b5c9-65ec51aa34c7 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2025-02-19T04:36:37Z |
| publishDate | 2025 |
| publisher | Springer Nature [academic journals on nature.com] |
| record_format | dspace |
| spelling | oxford-uuid:9e652c50-84b6-4352-b5c9-65ec51aa34c72025-02-01T20:10:23ZAI-assisted discovery of quantitative and formal models in social scienceJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:9e652c50-84b6-4352-b5c9-65ec51aa34c7EnglishJisc Publications RouterSpringer Nature [academic journals on nature.com]2025Balla, JHuang, SDugan, ODangovski, RSoljačić, MIn social science, formal and quantitative models, ranging from ones that describe economic growth to collective action, are used to formulate mechanistic explanations of the observed phenomena, provide predictions, and uncover new research questions. Here, we demonstrate the use of a machine learning system to aid the discovery of symbolic models that capture non-linear and dynamical relationships in social science datasets. By extending neuro-symbolic methods to find compact functions and differential equations in noisy and longitudinal data, we show that our system can be used to discover interpretable models from real-world data in economics and sociology. Augmenting existing workflows with symbolic regression can help uncover novel relationships and explore counterfactual models during the scientific process. We propose that this AI-assisted framework can bridge parametric and non-parametric models commonly employed in social science research by systematically exploring the space of non-linear models and enabling fine-grained control over expressivity and interpretability. |
| spellingShingle | Balla, J Huang, S Dugan, O Dangovski, R Soljačić, M AI-assisted discovery of quantitative and formal models in social science |
| title | AI-assisted discovery of quantitative and formal models in social science |
| title_full | AI-assisted discovery of quantitative and formal models in social science |
| title_fullStr | AI-assisted discovery of quantitative and formal models in social science |
| title_full_unstemmed | AI-assisted discovery of quantitative and formal models in social science |
| title_short | AI-assisted discovery of quantitative and formal models in social science |
| title_sort | ai assisted discovery of quantitative and formal models in social science |
| work_keys_str_mv | AT ballaj aiassisteddiscoveryofquantitativeandformalmodelsinsocialscience AT huangs aiassisteddiscoveryofquantitativeandformalmodelsinsocialscience AT dugano aiassisteddiscoveryofquantitativeandformalmodelsinsocialscience AT dangovskir aiassisteddiscoveryofquantitativeandformalmodelsinsocialscience AT soljacicm aiassisteddiscoveryofquantitativeandformalmodelsinsocialscience |