arbiter
JournalsPricingAccount

Tailoring generative AI chatbots for multiethnic communities in disaster preparedness communication: extending the CASA paradigm

Xinyan Zhao et al.

Journal of Computer-Mediated Communication2025https://doi.org/10.1093/jcmc/zmae022article
AJG 3
Weight
0.63

What the paper says

This study is among the first to develop different prototypes of generative artificial intelligence (GenAI) chatbots powered by GPT-4 to communicate hurricane preparedness information to diverse residents. Drawing from the Computers Are Social Actors paradigm and the literature on disaster vulnerability and cultural tailoring, we conducted a between-subjects experiment with 441 Black, Hispanic, and Caucasian residents of Florida. Our results suggest that GenAI chatbots varying in tone formality and cultural tailoring significantly influence perceptions of their friendliness and credibility, which, in turn, relate to hurricane preparedness outcomes. These results highlight the potential of using GenAI chatbots to improve diverse communities’ disaster preparedness.

17 citations

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.1093/jcmc/zmae022

Or copy a formatted citation

@article{xinyan2025,
  title        = {{Tailoring generative AI chatbots for multiethnic communities in disaster preparedness communication: extending the CASA paradigm}},
  author       = {Xinyan Zhao et al.},
  journal      = {Journal of Computer-Mediated Communication},
  year         = {2025},
  doi          = {https://doi.org/https://doi.org/10.1093/jcmc/zmae022},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Tailoring generative AI chatbots for multiethnic communities in disaster preparedness communication: extending the CASA paradigm

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.63

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.66 × 0.4 = 0.26
M · momentum0.93 × 0.15 = 0.14
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.