Dialogues with a pro-climate AI chatbot reduce climate change skepticism and inaction
Year: 2026
Type: preprint
Study designs: Randomized Controlled Trial, Clinical Trial
Abstract: Generic climate communication interventions often have modest effects on beliefs and very limited effects on climate action. We, thus, ask whether facts and evidence - tailored by an AI (a large language model, LLM) to address each person’s specific reservations - can address climate skepticism and inaction. Across two experiments, participants first described their main climate change reservation and then either engaged in a dialogue with an LLM (GPT-4-turbo) addressing it, discussed an unrelated topic with an LLM before receiving information about the scientific consensus on climate change (“standard-of-care”), or discussed an unrelated topic with an LLM alone (control; included only in the first experiment). We find that the LLM treatment substantially reduces participants’ conviction in their specific reservations, while the effects of consensus messaging are non-significant. Both treatments have effects, albeit small, on general pro-climate beliefs and attitudes. Critically, we find that the LLM treatment is more effective particularly for increasing willingness to make sacrifices to address climate change and donations to a pro-climate charity. These findings demonstrate that conversations with an AI may be an effective climate communication strategy, if people choose to interact with the bot.
Source: PsyArXiv (OSF Preprints)
Language: English
Subfield: Sociology and Political Science
Field: Social Sciences
Domain: Social Sciences
SDG: Climate action
Open Access status: green
OpenAlex ID: W7166425906