ORIGINAL RESEARCH article
Front. Artif. Intell.
Sec. AI for Human Learning and Behavior Change
This article is part of the Research TopicAI Behavioral Science: Understanding, Modeling, and Aligning AI BehaviorsView all 3 articles
Theory-Based Digital Twin Simulations of Crisis Messaging Digital Twin Simulations of Theory-Driven Crisis Messaging During Hurricane Evacuations in Synthetic Populations: A Miami-Dade County Case Study
Provisionally accepted
Brandon Walling*
Linda Desens*
Rhys O'Neill*
Vanessa Howard
Mary GiammarinoDenise Scannell*Beth Elson
Scott Rosen- The MITRE Corporation, McLean, United States
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Digital twin and agentic artificial intelligence technology provide innovative systems for testing theory and behavioral science, which can improve emergency communication in crisis situations. More advanced and effective evidence-based messaging is needed for better safety preparation for extreme weather and more trusted geospatial-specific evacuation communication for dangerous conditions. This research involves the design and application of a digital twin to study and refine crisis messages before they are used in real emergencies, giving agencies a proof-of-concept approach to improve communication and disaster readiness. This study involves the development and testing of a synthetic population within a digital twin of Miami Dade County as well as the development of a Message Assessment Framework (MAF) based on the Extended Parallel Process Model (EPPM) and the Theory of Planned Behavior (TPB) to design the messages. Agents were exposed to fear-only, efficacy-only, norm-only, combined fear+efficacy, combined fear+efficacy+norm, and a neutral control message. The results showed that messages grounded in behavioral theory were more effective than the control message at encouraging evacuation. Messages that combined fear and efficacy provided the best results in the synthetic population's decision to evacuate, while adding social norm cues did not produce a clear added benefit.
Keywords: agentic AI, artificial intelligence, autonomous agents, Behavioral Science Theories, crisis communication, crisis management, Digital Twins, Evacuation
Received: 29 Sep 2025; Accepted: 26 Jan 2026.
Copyright: © 2026 Walling, Desens, O'Neill, Howard, Giammarino, Scannell, Elson and Rosen. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Brandon Walling
Linda Desens
Rhys O'Neill
Denise Scannell
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.