Our socio-infrastructure systems are becoming more and more vulnerable due to the increased severity and frequency of extreme events every year. Effective disaster management can minimize the damaging impacts of a disaster to a large extent. The ubiquitous use of social media platforms in GPS enabled smartphones offers a unique opportunity to observe, model, and predict human behavior during a disaster. This dissertation explores the opportunity of using social media data and different modeling techniques towards understanding and managing disaster more dynamically. In this dissertation, we focus on four objectives. First, we develop a method to infer individual evacuation behaviors (e.g., evacuation decision, timing, destination) from social media data. We develop an input output hidden Markov model to infer evacuation decisions from user tweets. Our findings show that using geo-tagged posts and text data, a hidden Markov model can be developed to capture the dynamics of hurricane evacuation decision. Second, we develop evacuation demand prediction model using social media and traffic data. We find that trained from social media and traffic data, a deep learning model can predict well evacuation traffic demand up to 24 hours ahead. Third, we present a multi-label classification approach to identify the co-occurrence of multiple types of infrastructure disruptions considering the sentiment towards a disruption—whether a post is reporting an actual disruption (negative), or a disruption in general (neutral), or not affected by a disruption (positive). We validate our approach for data collected during multiple hurricanes. Fourth, finally we develop an agent-based model to understand the influence of multiple information sources on risk perception dynamics and evacuation decisions. In this study, we explore the effects of socio-demographic factors and information sources such as social connectivity, neighborhood observation, and weather information and its credibility in forming risk perception dynamics and evacuation decisions.
If this is your thesis or dissertation, and want to learn how to access it or for more information about readership statistics, contact us at STARS@ucf.edu
Doctor of Philosophy (Ph.D.)
College of Engineering and Computer Science
Civil, Environmental and Construction Engineering
Length of Campus-only Access
Doctoral Dissertation (Open Access)
Roy, Kamol Chandra, "Understanding the Socio-infrastructure Systems During Disaster from Social Media Data" (2020). Electronic Theses and Dissertations, 2020-. 410.