Modeling the Influence of Online Social Media Information on Post-Disaster Mobility Decisions

Takahiro Yabe,Satish V Ukkusuri,P Suresh C Rao

doi:10.3390/su13095254

Takahiro Yabe, Satish V Ukkusuri + Show 1 more

Open Access

https://doi.org/10.3390/su13095254

Copy DOI

Journal: Sustainability	Publication Date: May 8, 2021
Citations: 10	License type: CC BY 4.0

Affiliation: Purdue University West Lafayette

Abstract

Disaster risk management, including response and recovery, are essential elements of sustainable development. With the recent increase in natural hazards, the importance of techniques to understand, model and predict the evacuation and returning behavior of affected individuals is rising. Studies have found that influence from real world social ties affects mobility decisions during disasters. Despite the rapid spread of social media platforms, little has been quantitatively understood about the influence of social ties on online social media on such decisions. Information provided by who at what timing influences users’ decision-making process by how much during disasters? In this study, we answer these research questions by proposing a data-driven framework that can predict post-disaster mobility decisions and simultaneously unravel the influence of various information on online social media. More specifically, our method quantifies the influence of information provided by different types of social media accounts on the peoples’ decisions to return or stay displaced after evacuation. We tested our approach using real world data collected from more than 13 million unique Twitter users during Hurricane Sandy. Experiments verified that we can improve the predictive accuracy of return and displacement behavior, and also quantify the influence of online information. In contrast to popular beliefs, it was found that information posted by the crowd influenced the decisions more than information disseminated by official accounts. Improving our understanding of influence dynamics on online social media could provide policy makers with insights on how to disseminate information on social media more effectively for better disaster response and recovery, which may contribute towards building sustainable urban systems.

Highlights

Disaster risk management, including response and recovery, are essential elements of sustainable development [1,2,3]
We model the influence of online social media information on postIn this paper, we model the influence of online social media information on postdisaster mobility decisions using a data-driven, network approach
The tweets posted by media outlet accounts (“Media”) show negativity especially during the landfall of the hurricane, and stay negative for at least

Summary

Introduction

Disaster risk management, including response and recovery, are essential elements of sustainable development [1,2,3]. Studies using household surveys and focus group interviews have revealed the effect of various factors on the decision-making processes of the affected people during disasters Sociodemographic factors such as family membership, race, and income, hazard related factors including the intensity of the hazard and location of residence, and individual factors including past disaster experiences and risk perception, were shown to have influence on mobility decision making processes [5,6,7,8,9,10,11,12,13]. Studies have modeled the influence of real-world social network ties on post-disaster mobility decisions using statistical model [15] and simulation approaches [16]

Methods

Results

Discussion

Conclusion