EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Generative Multimodal Models for Social Science: An Application with Satellite and Streetscape Imagery

Tina Law, Elizabeth Roberto

Sociological Methods & Research · 2025-08 · 54 (3) · 889-932

DOI: 10.1177/00491241251339673 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sociological Methods & Research, online erschienen am 27.05.2025. Verfasst von Tina Law und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 100 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Rice University BRIDGE Seed Grant.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Although there is growing social science research examining how generative AI models can be effectively and systematically applied to text-based tasks, whether and how these models can be used to analyze images remain open questions. In this article, we introduce a framework for analyzing images with generative multimodal models, which consists of three core tasks: curation, discovery, and measurement and inference. We demonstrate this framework with an empirical application that uses OpenAI's GPT-4o model to analyze satellite and streetscape images ( n = 1,101) to identify built environment features that contribute to contemporary residential segregation in U.S. cities. We find that when GPT-4o is provided with well-defined image labels, the model labels images with high validity compared to expert labels. We conclude with thoughts for other use cases and discuss how social scientists can work collaboratively to ensure that image analysis with generative multimodal models is rigorous, reproducible, ethical, and sustainable.

Förderung

  • Rice University BRIDGE Seed Grant

Zitieren

APA

Law, T., & Roberto, E. (2025). Generative Multimodal Models for Social Science: An Application with Satellite and Streetscape Imagery. Sociological Methods & Research, 54(3), 889-932. https://doi.org/10.1177/00491241251339673

Vancouver

Law T, Roberto E. Generative Multimodal Models for Social Science: An Application with Satellite and Streetscape Imagery. Sociological Methods & Research. 2025;54(3):889-932. doi:10.1177/00491241251339673

BibTeX
@article{Law2025,
  author = {Law, Tina and Roberto, Elizabeth},
  title = {Generative Multimodal Models for Social Science: An Application with Satellite and Streetscape Imagery},
  journal = {Sociological Methods & Research},
  year = {2025},
  volume = {54},
  number = {3},
  pages = {889--932},
  doi = {10.1177/00491241251339673}
}
Kostenlos starten →