Lee, Amy S.G.Kirkland, KellyStanley, Samantha K.Robinson, AbbyLeviston, ZoeWalker, Iain2025-05-232025-05-232045-2322ORCID:/0000-0002-4969-7916/work/184100282http://www.scopus.com/inward/record.url?scp=105003170521&partnerID=8YFLogxKhttps://hdl.handle.net/1885/733752964What do Australians believe would change their current opinions about climate change? In this study, we used audience segmentation analysis through the Six Americas Short Survey to identify groups of climate opinion holders within a representative sample of Australians. We had 4857 participants tell us what it would take to change their current opinions about climate change and leveraged OpenAI’s Generative Pre-Trained Transformer (GPT) to identify the presence or absence of themes (Nothing, Evidence and Information, Trusted Sources, Action, and Unsure) and subthemes in their responses. GPT performed at near-human levels, proving to be a highly useful tool for thematic analysis. Our analyses revealed that strong climate denialists and believers tended to display greater dogmatism, with increased likelihood of stating that nothing would change their mind and lower likelihood of being unsure. Results also highlighted the need for diverse forms of evidence and information and the importance of trusted sources of information across audience segments. These findings provide support for GPT’s utility in managing large datasets in the social sciences and offer participant-informed insights into climate opinion change.Data collection was paid using research funds provided to Iain Walker by the Research School of Psychology at the Australian National University and by the Melbourne School of Psychological Sciences at the University of Melbourne. Samantha K. Stanley is the recipient of an Australian Research Council Discovery Early Career Award (DE240100001) funded by the Australian Government.14en© The Author(s) 2025.Audience segmentationChat GPTClimate changeLarge language modelsOpinion changeSix Americas202510.1038/s41598-025-96714-z105003170521