Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/10617
Title: AI for Climate Justice: Assessing Large Language Models from an Intersectional Lens
Authors: Nguyen, Victoria
Nguyen, Ha
King, Hunter
Ludovise, Sara
Santagata, Rossella
Keywords: Learning Sciences
Issue Date: 2024
Publisher: International Society of the Learning Sciences
Citation: Nguyen, V., Nguyen, H., King, H., Ludovise, S., & Santagata, R. (2024). AI for Climate Justice: Assessing Large Language Models from an Intersectional Lens. In Lindgren, R., Asino, T. I., Kyza, E. A., Looi, C. K., Keifert, D. T., & Suárez, E. (Eds.), Proceedings of the 18th International Conference of the Learning Sciences - ICLS 2024 (pp. 1055-1058). International Society of the Learning Sciences.
Abstract: Generative Artificial Intelligence (AI) tools, including language models that can create novel content, have shown promise for science communication at scale. However, these tools may show inaccuracies and biases, particularly against marginalized populations. In this work, we examined the potential of GPT-4, a generative AI model, in creating content for climate science communication. We analyzed 100 messages generated by GPT-4 that included descriptors of intersecting identities, science communication mediums, locations, and climate justice issues. Our analyses revealed that community awareness and actions emerged as prominent themes in the generated messages, while systemic critiques of climate justice issues were not as present. We discuss how intersectional lenses can help researchers to examine the underlying assumptions of emerging technology before its integration into learning contexts.
Description: Short Paper
URI: https://doi.org/10.22318/icls2024.120847
https://repository.isls.org//handle/1/10617
Appears in Collections:ISLS Annual Meeting 2024

Files in This Item:
File SizeFormat 
ICLS2024_1055-1058.pdf286.35 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.