Appraising Situational Awareness
This research focus on leveraging social media data (i.e. Twitter) to comprehensively assess public dynamic situational awareness during 2020 wildfire season at the city-level. In this study, I employed Bidirectional Encoder Representations from Transformers (BERT) topic modeling to cluster Twitter data and conducted a temporal-spatial analysis to understand topic distribution across various regions. Additionally, I integrated the Susceptible-Infected-Recovered (SIR) model to quantitatively measure the extent and speed of topic diffusion, facilitating more precise resource allocation. The results of the temporal-spatial analysis highlighted a close alignment between topic diffusion and wildfire locations and timelines, showcasing the real-time nature of Twitter discussions in response to unfolding events. Moreover, the findings from the topic-based SIR model revealed that the pace of topic diffusion corresponded with wildfire propagation patterns, reflecting varying levels of public awareness and responses. Furthermore, the study underscored the diversity of concerns expressed by different communities, emphasizing the need to tailor disaster responses to meet local needs effectively.
Article
Zihui Ma, Lingyao Li, Libby Hemphill, Greagy B. Baecher and Yubai Yuan. “Investigating disaster response through social media data and the Susceptible-Infected-Recovered (SIR) model: A case study of 2020 Western U.S. wildfire season.” Sustainable Cities and Society.
Effective disaster response is critical for communities to remain resilient and advance the development of smart cities. Responders and decision-makers would 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. We used Bidirectional Encoder Representations from Transformers (BERT) topic modeling to cluster topics from Twitter data. Then, we conducted a temporal-spatial analysis to examine the distribution of these topics across different regions during the 2020 western U.S. wildfire season. Our results show that Twitter users mainly focused on three topics: “health impact,” “damage,” and “evacuation.” We used the Susceptible-Infected-Recovered (SIR) theory to explore the magnitude and velocity of topic diffusion on Twitter. The results displayed a clear relationship between topic trends and wildfire propagation patterns. The estimated parameters obtained from the SIR model in selected cities revealed that residents exhibited a high level of several concerns during the wildfire. Our study offers a quantitative approach to measure disaster response and support community resilience enhancement.
Conference proceedings
Zihui Ma, Lingyao Li, Yubai Yuan, Greagy B. Baecher. (2023) “Appraising Situational Awareness in Social Media Data for Wildfire Response.” ASCE Inspire conference, Arlington, Virginia, November 16 – 18, 2023.