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

Dublin Core

Title

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

Subject

generative AI, chatbots, disaster communication, multiethnic communities, humanness, cultural tailoring.

Description

This study is among the first to develop different prototypes of generative artificial intelligence (GenAI) chatbots powered by GPT-4 to communi-
cate hurricane preparedness information to diverse residents. Drawing from the Computers Are Social Actors paradigm and the literature on di-
saster 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 friendli-
ness 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.

Creator

Xinyan Zhao 1,�, Yuan Sun 2

, Wenlin Liu2

, Chau-Wai Wong3

Source

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

Date

November 18, 2024

Contributor

PERI IRAWAN

Format

PDF

Language

ENGLISH

Type

TEXT

Files

Collection

Citation

Xinyan Zhao 1,�, Yuan Sun 2 , Wenlin Liu2 , Chau-Wai Wong3, “Tailoring generative AI chatbots for multiethnic
communities in disaster preparedness communication:
extending the CASA paradigm,” Repository Horizon University Indonesia, accessed May 22, 2025, https://repository.horizon.ac.id/items/show/8820.