Adaptive model reveals local feelings during wildfires and hurricanes
Beyond What Is Visible: Context-Aware Sentiment Across Online Communities Among Crisis Events
Computers and Society
Summary
Social media shows how people feel during disasters, but not everyone affected posts online, which can make the picture incomplete. The authors created a model that mixes text from social media with information about movement and community features to better understand emotions across different cities during crises. Their model works better than just using text alone, especially where online posts are few. It also shows how feelings and movement patterns relate differently depending on the disaster.
What this means in practice
- •For emergency response teams: Enhance disaster impact assessments by incorporating adaptive sentiment models to capture community emotions even in offline or low-data areas.
- •For urban planners: Improve understanding of local community stress and mobility changes during crises to inform resilient city design and resource deployment.
Authors
Zihui Ma, Yiheng Chen, Lingyao Li, Chen Chen, Fan Yang, Xiao Huang, Haozheng Liu, Yuhan Wang, Runlong Yu, Gregory B. Baecher
Abstract
Social media offers timely insight into disaster experiences, yet online communities may not represent those affected on the ground. Uneven participation can bias crisis information systems toward data-rich locations and obscure communities with fewer digital traces. We address this with an adaptive cross-community learning framework that combines text and aggregate mobility signals with socioeconomic and hazard-informed community representations, supplementing sparse local observations with evidence from structurally related cities. We evaluate the framework on the January 2025 Southern California wildfires and 2024 Hurricane Helene in Florida. The adaptive model achieves the highest F1-score in both cases (0.5923 and 0.7615), while augmentation has its strongest effect where original observations are limited. The framework also reveals finer cross-city community-level sentiment variation and stronger sentiment-mobility correspondence than text-only models, with relationships differing across disaster contexts. These findings support crisis systems that better account for context-dependent evidence and improve interpretation of underrepresented community signals.