Large language models accurately predict public perceptions of support for climate action worldwide
This provides a rapid tool for assessing perception gaps in climate action, potentially reducing reliance on costly surveys, though it is incremental as it applies existing LLMs to a new social science problem.
The study tested whether large language models (LLMs) can predict global public perceptions of support for climate action, finding that LLMs, especially Claude, accurately estimated these perceptions with a mean absolute error of about 5 percentage points and a correlation of 0.77, comparable to statistical models.
Although most people support climate action, widespread underestimation of others' support stalls individual and systemic changes. In this preregistered experiment, we test whether large language models (LLMs) can reliably predict these perception gaps worldwide. Using country-level indicators and public opinion data from 125 countries, we benchmark four state-of-the-art LLMs against Gallup World Poll 2021/22 data and statistical regressions. LLMs, particularly Claude, accurately capture public perceptions of others' willingness to contribute financially to climate action (MAE approximately 5 p.p.; r = .77), comparable to statistical models, though performance declines in less digitally connected, lower-GDP countries. Controlled tests show that LLMs capture the key psychological process - social projection with a systematic downward bias - and rely on structured reasoning rather than memorized values. Overall, LLMs provide a rapid tool for assessing perception gaps in climate action, serving as an alternative to costly surveys in resource-rich countries and as a complement in underrepresented populations.