Red Cards for Climate Myths: introducing ClimaVAR, an AI-based Tool for Climate Disinformation Detection

Marcos A. de Oliveira Jr.; Gail Whiteman; Nectarios K. Nugroho; Ashish Siwach; Gerson G. H. Cavalheiro

doi:10.5753/semish.2026.21813

Marcos A. de Oliveira Jr. University of Exeter / IFFar / UFRGS https://orcid.org/0000-0001-7160-3720
Gail Whiteman University of Exeter https://orcid.org/0000-0002-4152-5538
Nectarios K. Nugroho University of Exeter https://orcid.org/0009-0002-5343-7348
Ashish Siwach University of Exeter https://orcid.org/0000-0001-5403-1185
Gerson G. H. Cavalheiro UFPel https://orcid.org/0000-0002-4314-3429

DOI: https://doi.org/10.5753/semish.2026.21813

Resumo

Climate disinformation undermines public understanding, erodes trust in science, and delays effective climate action. This paper introduces ClimaVAR, an AI-based tool that uses a football referee metaphor to evaluate climate-related statements. ClimaVAR proposes a pipeline which, from a user textual input, combines: (i) climate disinformation detection using Computer-assisted recognition of (climate change) denial and skepticism (CARDS) model, (ii) Retrieval-Augmented Generation (RAG) from curated scientific documents to find correct statements when disinformation is detected, and (iii) a large language model layer to generate accessible answers translating climate science into football metaphors. The system analyzes user-submitted climate statements and issues football-related messages (offside, yellow/red card, goal) indicating alignment or not with truth, accompanied by explanations and scientific references. Deployed at high-profile events including COP30 and side events at Davos, during the World Economic Forum 2026, ClimaVAR has demonstrated the potential of culturally adapted interfaces to increase engagement with climate science. Initial results demonstrated that 66% of user inputs were tagged as misinformation. Complementary analyses enabled also grouping inputs by topic, with themes such as: Climate Denial & Skepticism, Human Causation & Consensus, Physical Impacts & Extreme Events, Energy & Policy, and Other/Emerging Topics.

Referências

Amazeen, M. A. (2020). Journalistic interventions: The structural factors affecting the global emergence of fact-checking. Journalism, 21(1):95–111.

Basol, M., Roozenbeek, J., and van der Linden, S. (2020). Good news about bad news: Gamified inoculation boosts confidence and cognitive immunity against fake news. Journal of Cognition, 3(1):2.

Boykoff, M. T. (2007). Flogging a dead norm? newspaper coverage of anthropogenic climate change in the united states and united kingdom from 2003 to 2006. Area, 39(4):470–481.

Coan, T. G., Cook, J., and Lewandowsky, S. (2024). Augmented detection of climate contrarian claims using hierarchical classification. Environmental Communication, 18(3):342–359.

Coan, T. G., Vokey, B., Cook, J., and Lewandowsky, S. (2021). Computer-assisted classification of contrarian claims about climate change. Scientific Reports, 11(1):22320.

Cook, J., Lewandowsky, S., and Ecker, U. K. (2017a). Deconstructing climate misinformation to identify reasoning errors. Environmental Research Letters, 12(2):024018.

Cook, J., Lewandowsky, S., and Ecker, U. K. (2017b). Neutralizing misinformation through inoculation: Exposing misleading argumentation techniques reduces their influence. PLOS ONE, 12(5):e0175799.

Cook, J., Oreskes, N., Doran, P. T., Anderegg, W. R., Verheggen, B., Maibach, E. W., Carlton, J. S., Lewandowsky, S., Skuce, A. G., Green, S. A., et al. (2016). Consensus on consensus: a synthesis of consensus estimates on human-caused global warming. Environmental Research Letters, 11(4):048002.

Dunlap, R. E. and Jacques, P. J. (2013). Climate change skepticism and denial: An introduction. American Behavioral Scientist, 57(6):691–698.

Falkenberg, M., Galeazzi, A., Torricelli, M., Di Marco, N., Larosa, F., Sas, M., Metta, A., Quattrociocchi, W., and Zollo, F. (2022). Growing polarization around climate change on social media. Nature Climate Change, 12(12):1114–1121.

Farkas, B. and Derczynski, L. (2022). Scalable and automated detection of climate misinformation using natural language processing. Patterns, 3(9):100579.

Lamb, W. F., Mattioli, G., Levi, S., Roberts, J. T., Capstick, S., Creutzig, F., Minx, J. C., Müller-Hansen, F., Culhane, T., and Steinberger, J. K. (2020). Discourses of climate delay. Global Sustainability, 3:e17.

Li, Z., Wang, Y., Chen, Z., and Liu, Y. (2024). Multimodal misinformation detection using vision-language models. Proceedings of the AAAI Conference on Artificial Intelligence, 38(17):18750–18758.

Maertens, R., Roozenbeek, J., Basol, M., and van der Linden, S. (2021). Long-term effectiveness of inoculation against misinformation: Three longitudinal experiments. Journal of Experimental Psychology: Applied, 27(1):1–16.

Moser, S. C. (2010). Communicating climate change: history, challenges, process and future directions. Wiley Interdisciplinary Reviews: Climate Change, 1(1):31–53.

Newman, N., Fletcher, R., Robertson, C. T., Eddy, K., and Nielsen, R. K. (2023). Information disorder and climate change. Reuters Institute for the Study of Journalism.

Oreskes, N. and Conway, E. M. (2010). Merchants of doubt: How a handful of scientists obscured the truth on issues from tobacco smoke to global warming. Bloomsbury Publishing USA.

Pearce, W., Grundmann, R., Hulme, M., Raman, S., Kershaw, E. H., and Tsouvalis, J. (2019). Climate communication and sports: leveraging football for climate action. Climatic Change, 157(2):115–130.

Santos, Y., Silva, M., and Reis, J. C. S. (2023). Imagefactck.br: Repositório de imagens para a detecção de desinformação disseminada em plataformas digitais. In Anais do V Dataset Showcase Workshop, pages 87–98, Porto Alegre, RS, Brasil. SBC.

Silva, J., Silva, T., Lima, M., and Souza, R. (2019). Aplicação do design centrado em humano para desenvolvimento de uma solução de software baseada em informações do tempo e clima. In Anais do X Workshop de Computação Aplicada a Gestão do Meio Ambiente e Recursos Naturais, pages 107–116, Porto Alegre, RS, Brasil. SBC.

Supran, G., Rahmstorf, S., and Oreskes, N. (2023). Assessing exxonmobil’s global warming projections. Science, 379(6628):eabk0063.

Treen, K. M. d., Williams, H. T., and O’Neill, S. J. (2020). Online misinformation about climate change. Wiley Interdisciplinary Reviews: Climate Change, 11(5):e665.

Vosoughi, S., Roy, D., and Aral, S. (2018). The spread of true and false news online. Science, 359(6380):1146–1151.

Williams, H. T., McMurray, J. R., Kurz, T., and Lambert, F. H. (2015). Network analysis reveals open forums that coordinate attack campaigns against climate science. Nature Climate Change, 5(6):563–567.

Zanartu, F., Blanco-Arancibia, C., Lewandowsky, S., and Cook, J. (2024). A technocognitive approach to detecting fallacies in climate misinformation. Scientific Reports, 14:25193.

Zhao, Y., Zhang, D., and Yang, J. (2023). Automated detection of climate change misinformation with large language models. Nature Communications, 14:6670.