Assistant Professor Tina Law publishes two new articles in Sociological Methods and Research
Assistant Professor Tina Law recently published two new articles on generative AI in Sociological Methods & Research. She was the lead author for the article titled “Generative Multimodal Models for Social Science: An Application with Satellite and Streetscape Imagery.” This article introduces a methodological framework for analyzing images with generative multimodal models—AI models that are trained to engage with multiple modalities (e.g., text, image, audio)—and demonstrates this framework with an empirical application that uses OpenAI’s gpt-4o model to analyze satellite and streetscape images to identify built environment features that contribute to contemporary residential segregation in U.S. cities. This article is co-authored with Elizabeth Roberto.
Professor Law co-authored another article titled “Updating “The Future of Coding:” Qualitative Coding with Generative Large Language Models” with Nga Than, Leanne Fan, Laura Nelson, and Leslie McCall. This article tests the ability of closed and open-source generative large language models to replicate and augment traditional qualitative coding with an empirical application focused on identifying U.S. news articles published between 1980 and 2012 that discuss the complex concept of economic inequality.
These articles are part of an upcoming Sociological Methods & Research special issue on applications of generative AI for social science research.