Authors: Yago Martin Gonzalez*, University of South Carolina
Topics: Hazards, Risks, and Disasters, Behavioral Geography
Keywords: Migration, displacement, tourism, Hurricane Maria, Puerto Rico, Big Data
Session Type: Paper
Start / End Time: 11:10 AM / 12:25 PM
Room: Colorado, Sheraton, IM Pei Tower, Majestic Level
Presentation File: No File Uploaded
The study of post-disaster population movements continues to be a major endeavor for authorities and researchers and many have called for innovative data-collection methods to complement traditional approaches. In this study, we examine the suitability of Twitter data for the assessment of the population disruptions triggered by Hurricane Maria in Puerto Rico. The results confirm the potential for using passive citizen sensor data (Twitter) to estimate the magnitude, timing, destination, and return of the displacement, as well as the extent of the impact on the arrival of non-residents to the island. The findings, consistent with early reports on post-Maria displacement/migration, revealed an off-island long-term displacement of nearly 4% of the Twitter sample. Non-resident visits fell significantly throughout Puerto Rico in the months after the hurricane, although we recognize important differences between high-season / low-season periods and across regions of the island.