HYBRID EVENT

Displacement and Return in the Internet Era: Social Media for Monitoring Migration Decisions in Northern Syria

Erin Elizabeth Walk
Max Planck Institute for Demographic Research (MPIDR), July 26, 2023

Abstract

According to UNHCR reporting there are over 27 million refugees globally, many of whom are hosted in neighboring countries which struggle with bureaucracy and service provision to support them. With the onset of Covid-19 in early 2020, gathering data on the location and conditions of these refugees has become increasingly difficult. Using Syria as a case study, where since 2011 80\% of the population has been displaced in the civil war, this paper shows how the widespread use of social media could be used to monitor migration of refugees. Using social media text and image data from three popular platforms (Twitter, Telegram, and Facebook), and leveraging survey data as a source of ground truth on the presence of IDPs and returnees, it uses topic modeling and image analysis to find that areas without return have a higher prevalence of violence-related discourse and images while areas with return feature content related to services and the economy. Building on these findings, the paper uses mixed effects models to show that these results hold pre- and post- return as well as when migration is quantified as monthly population flows. Monitoring refugee return in war prone areas is a complex task and social media may provide researchers, aid groups, and policymakers with tools for assessing return in areas where survey or other data is unavailable or difficult to obtain.

About

Erin Elizabeth Walk is a PhD Candidate at Massachusetts Institute of Technology (MIT) and a graduate fellow at MIT Global Diversity Lab. Erin has a degree in Mechanical Engineering and a minor in Government from Harvard University. Before starting her PhD studies at MIT, she has worked as a policy analyst at Cloudfare (Washington, DC).

Erin’s research focuses on using large datasets, primarily social media data, to understand conflict, migration, and polarization. More specifically, she is interested in the ways in which online data can be used to support vulnerable, diverse, and hard to reach populations, how such information can be combined with traditional data sources, as well as internet accessibility and freedom of expression online. Her research uses probabilistic machine learning and natural language processing as methods.