Vox Populi, Vox AI? Using Language Models to Estimate German Public Opinion

TL;DR

This study evaluates GPT-3.5's ability to estimate German public opinion on vote choice, revealing biases and limitations in predicting individual and subgroup voting behaviors compared to survey data.

Contribution

It provides a novel analysis of LLMs' capacity to estimate public opinion in a non-US context, highlighting their biases and contextual limitations.

Findings

GPT-3.5 does not accurately predict individual vote choices.

The LLM shows bias towards Green and Left parties.

It captures tendencies of typical voter subgroups but misses complex individual factors.

Abstract

The recent development of large language models (LLMs) has spurred discussions about whether LLM-generated "synthetic samples" could complement or replace traditional surveys, considering their training data potentially reflects attitudes and behaviors prevalent in the population. A number of mostly US-based studies have prompted LLMs to mimic survey respondents, with some of them finding that the responses closely match the survey data. However, several contextual factors related to the relationship between the respective target population and LLM training data might affect the generalizability of such findings. In this study, we investigate the extent to which LLMs can estimate public opinion in Germany, using the example of vote choice. We generate a synthetic sample of personas matching the individual characteristics of the 2017 German Longitudinal Election Study respondents. We ask the LLM GPT-3.5 to predict each respondent's vote choice and compare these predictions to the survey-based estimates on the aggregate and subgroup levels. We find that GPT-3.5 does not predict citizens' vote choice accurately, exhibiting a bias towards the Green and Left parties. While the LLM captures the tendencies of "typical" voter subgroups, such as partisans, it misses the multifaceted factors swaying individual voter choices. By examining the LLM-based prediction of voting behavior in a new context, our study contributes to the growing body of research about the conditions under which LLMs can be leveraged for studying public opinion. The findings point to disparities in opinion representation in LLMs and underscore the limitations in applying them for public opinion estimation.