NATURAL LANGUAGE PROCESSING, SOCIAL MEDIA, AND EPIDEMIC MODEL-ING FOR WILDFIRE RESPONSE AND RE-SILIENCE ENHANCEMENT

Abstract

Effective disaster response is critical for communities to remain resilient and advance the development of smart cities. Responders and decision-makers benefit from reliable, timely measures of the issues impacting their communities during a disaster, and social media offers a potentially rich data source. Social media can reflect public concerns and behaviors during a disaster, offering valuable insights for decision-makers to understand evolving situations and optimize resource allocation. A comprehensive literature review of natural language processing (NLP) of social media data in disaster management, covering 324 articles published between 2011 and 2022, revealed a gap in applying NLP techniques to wildfire scenarios. Meanwhile, the increasing frequency of wildfires highlights the need for advanced management tools. To address this, we integrated the BERTopic and SIR models to capture public responses on Twitter during the 2020 western U.S. wildfire season, analyzing both the magnitude and velocity of topic diffusion. The results displayed a clear relationship between topic trends and wildfire propagation patterns. The parameters estimated from the SIR model for selected cities revealed that residents expressed various levels of concern or demand during wildfires. The study also demonstrated a practical framework for utilizing social media data to aid wildfire evacuations. Through social network analysis, we clarified the roles of key information disseminators and provided guidelines for extracting high-priority information. Although biases in social media and model limitations exist, the study offers qualitative and quantitative approaches to investigate wildfire response and sup-port community resilience enhancement.