Work

Using Artificial Intelligence to Generate Visual Vignettes in Factorial Survey Experiments

Year: 2025

Type: article

Abstract: Factorial survey experiments are widely used in the social sciences to study decision-making and attitudes through controlled, experimentally manipulated scenarios—typically presented as text. However, textual vignettes may limit the realism of vignettes and participant en-gagement, motivating the search for alternative approaches. This article explores how gener-ative artificial intelligence (AI) can be used to create photorealistic, customisable images for visual vignettes. It demonstrates techniques for producing and selectively editing images, highlighting their potential addressing the demands of experimental social science research while also addressing key challenges, including ethical considerations, biases inherent in AI tools, and technical limitations. The article showcases potential applications of AI-generated images in social science research and presents survey results on how these images are per-ceived by participants. By critically evaluating both opportunities and challenges, this article provides researchers with practical guidance on integrating AI-generated visuals into factori-al survey experiments, enhancing methodological approaches in the social sciences.

Source: Social Science Computer Review

DOI: 10.1177/08944393251392916

Author: Nicole Schwitter

Institutions: University of Mannheim, University of Warwick

Language: English

Topic: Survey Methodology and Nonresponse

Subfield: Sociology and Political Science

Field: Social Sciences

Domain: Social Sciences

Open Access status: hybrid

Estimated APC paid: $3,900

Funders: Deutsche Forschungsgemeinschaft, Universität Mannheim