Work

Simulating Crisis Cognition: A Computational Framework for Hypothesis Generation in Crisis Communication

Year: 2026

Type: conference-paper

Abstract: Large Language Models (LLMs) have demonstrated remarkable fidelity in simulating social dynamics, yet using them to inform high-stakes crisis policy requires rigorous causal evaluation.We introduce CRISIS COGNITION, a framework rooted in generative Structural Causal Models (SCM) that functions as an insilico hypothesis generator.By coupling realworld telemetry with 1,813 agents, we conduct a counterfactual simulation to evaluate communication strategies.Unlike prior descriptive work, we employ a Stratified Analysis to strictly control for personality confounders.Our simulations generate a computational hypothesis: within the LLM's generative process, emotional scaffolding serves as a functional prerequisite to unlock valid reasoning paths for high-neuroticism agents.Crucially, we identify a "Sedative Effect" in simultaneous interventions, confirming that the sequence of support is as vital as the content.This framework provides a rigorous testbed for evaluating strategies before human-subject trials.

Source: Findings of the Association for Computational Linguistics: ACL (Findings of ACL)

DOI: 10.18653/v1/2026.findings-acl.692

Authors: Changsen Yuan, Yanghao Zhou, Chong Feng, Ge Shi

Institutions: Beijing Institute of Technology, Beijing University of Technology

Language: English

Topic: Public Relations and Crisis Communication

Subfield: Communication

Field: Social Sciences

Domain: Social Sciences

Open Access status: hybrid

Funder: Natural Science Foundation of Fujian Province

Award: G5627589539