Workshop Proceedings of the 20th International
AAAI Conference on Web and Social Media
Workshop: SocialLLM: Large Language Models for Social Reasoning and Simulation
DOI: 10.36190/2026.67Extant literature has rarely considered the cognitive aspects of an outbreak. Social psychology literature suggests that the mental construal of a specific event depends on psychological distance, i.e., the perceived distance from the event. Consequently, psychological distance can potentially influence (or even distort) the linguistic content of deliberations during outbreaks, making policy formulation based on such data problematic. Hence, we employed the theoretical lens of Construal-level Theory to understand the cognitive aspects of social media data during the 2014 Ebola outbreak and used these insights as input for our proposed generative agent-based policy formulation. The core contribution of this study is leveraging social media data for policymaking through generative agents and assessing the same by comparing the suggested policies with the original policy documents.