Utilizing Geo-tagged Tweets to Understand Evacuation Dynamics during Emergencies

Abstract

Hurricane evacuation is a complex process and a better understanding of the evacuation behavior of the coastal residents could be helpful in planning better evacuation policy. Traditionally, various aspects of the household evacuation decisions have been determined by post-evacuation questionnaire surveys, which are usually time-consuming and expensive. Increased activity of users on social media, especially during emergencies, along with the geo-tagging of the posts, provides an opportunity to gain insights into user's decision-making process, as well as to gauge public opinion and activities using the social media data as a supplement to the traditional survey data. This paper leverages the geo-tagged Tweets posted in the New York City (NYC) in wake of Hurricane Sandy to understand the evacuation behavior of the residents. Based on the geo-tagged Tweet locations, we classify the NYC Twitter users into one of the three categories: outside evacuation zone, evacuees, and non-evacuees and examine the types of Tweets posted by each group during different phases of the hurricane. We establish a strong link between the social connectivity with the decision of the users to evacuate or stay. We analyze the geo-tagged Tweets to understand evacuation and return time and evacuation location patterns of evacuees. The analysis presented in this paper could be useful for authorities to plan a better evacuation campaign to minimize the risk to the life of the residents of the emergency hit areas.

A review of social media use during disaster response and recovery phases

“…Social media data can also inform disaster recovery logistic assessments. Studies have used social media data from hurricanes to gauge evacuation patterns [68,69] which can then help to predict return behaviors of evacuees [70]. Evacuation patterns and return behaviors are vital information for disaster recovery planning and decisions.…”

“…• Social media platforms provided recovery and relief managers with useful information during the recovery process, including businesses re-openings, cleanup procedures, work responsibilities, school status, re-entry after evacuation, return of infrastructure, restoration of goods and services, donation of money or goods, fundraising activities, state of infrastructure repair, and volunteering [67]. • Social media could also inform disaster recovery logistic assessments, including evacuation and re-entry patterns key to recovery planning and decision-making [68][69][70]. • Social media allowed emergency managers to distinguish among the needs of its users located within disaster-affected areas [71].…”

“…• Social media can provide complementary information to other and possible more onerous sources of data from disaster events (i.e., shelter records, surveys, in-depth interviews, etc.) [68][69][70]. • Visual content shared through social media can help with spatial planning decisions.…”

“…Namely, advocating for social media users to turn on geo-tagging settings before, during, and after disasters can greatly increase the quantity and quality of the data and results [68][69][70]. • Emergency managers should consider social media as a mechanism to gauge recovery successes [24,72]; however, researchers should first engage with practitioners to develop an agreed-upon set of recovery and resilience indicators.…”

Análisis de la movilidad espacial de la población asociada a huracanes a partir de la sombra digital geoespacial derivada de Twitter

“…Martín et al (2017) introdujeron un método para estimar la obediencia de una evacuación obligatoria utilizando la sombra digital geoespacial de Twitter. Este método ha sido replicado más recientemente en otros eventos como el Huracán Sandy (Kumar and Ukkusuri, 2018). Estos estudios han revelado las ventajas que este tipo de datos ofrecen: son datos cada vez más comunes en la sociedad actual y en particular entre los segmentos más jóvenes de la población; existe capacidad de procesado y análisis en tiempo real; y son datos simples y de libre acceso, siempre condicionado por la capacidad computacional y las habilidades de programación Boletín de la Asociación de Geógrafos Españoles, 84, 2848, 1-35 del investigador.…”