In Silico Sociology: Forecasting COVID-19 Polarization with Large Language Models

TL;DR

This study demonstrates that large language models can accurately simulate political responses to COVID-19, revealing that polarization was largely predictable based on pre-existing discourse and ideological differences.

Contribution

The paper introduces a novel application of LLMs for sociological simulation, specifically reconstructing and analyzing political polarization related to COVID-19.

Findings

Simulated responses matched observed partisan differences in 84% of cases.

Partisan gaps were mainly due to differing appeals to freedom, safety, and trust.

COVID-19 polarization was largely consistent with prior ideological landscapes.

Abstract

By training deep neural networks on massive archives of digitized text, large language models (LLMs) learn the complex linguistic patterns that constitute historic and contemporary discourses. We argue that LLMs can serve as a valuable tool for sociological inquiry by enabling accurate simulation of respondents from specific social and cultural contexts. Applying LLMs in this capacity, we reconstruct the public opinion landscape of 2019 to examine the extent to which the future polarization over COVID-19 was prefigured in existing political discourse. Using an LLM trained on texts published through 2019, we simulate the responses of American liberals and conservatives to a battery of pandemic-related questions. We find that the simulated respondents reproduce observed partisan differences in COVID-19 attitudes in 84% of cases, significantly greater than chance. Prompting the simulated respondents to justify their responses, we find that much of the observed partisan gap corresponds to differing appeals to freedom, safety, and institutional trust. Our findings suggest that the politicization of COVID-19 was largely consistent with the prior ideological landscape, and this unprecedented event served to advance history along its track rather than change the rails.