Social media usage reveals how regions recover after natural disaster
Robert Eyre, Flavia De Luca, Filippo Simini
This repository contains code that can be used to reproduce the results found in the linked manuscript. Sample data is provided in the form of anonymised posting data which has had noise added to the posting date, along with the business id being replaced.
Abstract: The challenge of nowcasting the effect of natural disasters (e.g. earthquakes, floods, hurricanes) on assets, people and society is of primary importance for assessing the ability of such systems to recover from extreme events. Traditional disaster recovery estimates, such as surveys and interviews, are usually costly, time consuming and do not scale. Here we present a methodology to indirectly estimate the post-emergency recovery status ('downtime') of small businesses in urban areas looking at their online posting activity on social media. Analysing the time series of posts before and after an event, we quantify the downtime of small businesses for three natural disasters occurred in Nepal, Puerto Rico and Mexico. A convenient and reliable method for nowcasting the post-emergency recovery status of economic activities could help local governments and decision makers to better target their interventions and distribute the available resources more effectively.
arXiv link: https://arxiv.org/abs/1908.07384