Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Addressing Climate Action Misperceptions with Generative AI

Miriam Remshard, Yara Kyrychenko, Sander van der Linden, Matthew H. Goldberg, Anthony Leiserowitz, Elena Savoia, Jon Roozenbeek

TL;DR

While the personalised climate LLM did not outperform a web search in improving understanding of climate action impacts, the ability of LLMs to deliver personalised, actionable guidance may make them more effective at motivating impactful pro-climate behaviour change.

Abstract

Mitigating climate change requires behaviour change. However, even climate-concerned individuals often hold misperceptions about which actions most reduce carbon emissions. We recruited 1201 climate-concerned individuals to examine whether discussing climate actions with a large language model (LLM) equipped with climate knowledge and prompted to provide personalised responses would foster more accurate perceptions of the impacts of climate actions and increase willingness to adopt feasible, high-impact behaviours. We compared this to having participants run a web search, have a conversation with an unspecialised LLM, and no intervention. The personalised climate LLM was the only condition that led to increased knowledge about the impacts of climate actions and greater intentions to adopt impactful behaviours. While the personalised climate LLM did not outperform a web search in improving understanding of climate action impacts, the ability of LLMs to deliver personalised, actionable guidance may make them more effective at motivating impactful pro-climate behaviour change.

Addressing Climate Action Misperceptions with Generative AI

TL;DR

While the personalised climate LLM did not outperform a web search in improving understanding of climate action impacts, the ability of LLMs to deliver personalised, actionable guidance may make them more effective at motivating impactful pro-climate behaviour change.

Abstract

Mitigating climate change requires behaviour change. However, even climate-concerned individuals often hold misperceptions about which actions most reduce carbon emissions. We recruited 1201 climate-concerned individuals to examine whether discussing climate actions with a large language model (LLM) equipped with climate knowledge and prompted to provide personalised responses would foster more accurate perceptions of the impacts of climate actions and increase willingness to adopt feasible, high-impact behaviours. We compared this to having participants run a web search, have a conversation with an unspecialised LLM, and no intervention. The personalised climate LLM was the only condition that led to increased knowledge about the impacts of climate actions and greater intentions to adopt impactful behaviours. While the personalised climate LLM did not outperform a web search in improving understanding of climate action impacts, the ability of LLMs to deliver personalised, actionable guidance may make them more effective at motivating impactful pro-climate behaviour change.
Paper Structure (10 sections, 2 figures)

This paper contains 10 sections, 2 figures.

Table of Contents

  1. Results
  2. Discussion
  3. Methods
  4. Code and Data Availability
  5. Acknowledgements
  6. Author Contributions
  7. Competing Interests

Figures (2)

  • Figure 1: Study procedure as outlined in detail in the Methods section.
  • Figure 2: Comparison across conditions for a impact ranking accuracy and b intentions to engage in high-impact climate actions. For both panels, jittered points represent individual participants, bold diamond markers indicate condition means (M), and numeric labels report the mean value. Boxes show the interquartile range, with the central line indicating the median; whiskers extend to 1.5$\times$IQR. Horizontal brackets denote pairwise comparisons against the Personalized LLM condition. ${}^{*}$ indicates $p_{\text{Holm}} < .05$; ${}^{**}$ indicates $p < .01$ or $p_{\text{Holm}} < .02$. Asterisks shown in parentheses indicate effects that become marginally non-significant after Holm adjustment.