Tailoring Generative AI Chatbots for Multiethnic Communities in Disaster Preparedness Communication: Extending the CASA Paradigm

TL;DR

This study develops culturally tailored GPT-4 based chatbots to improve hurricane preparedness communication among diverse Florida residents, demonstrating that chatbot tone and cultural cues influence perceptions and preparedness outcomes.

Contribution

It introduces culturally tailored GenAI chatbot prototypes for disaster communication and empirically tests their impact on diverse community perceptions and behaviors.

Findings

Culturally tailored chatbots increase perceived friendliness and credibility.

Chatbot tone and cultural cues affect disaster preparedness perceptions.

GenAI chatbots can enhance communication effectiveness in multiethnic communities.

Abstract

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.