Can Internet search data be used as a proxy to predict refugee mobility? The soaring refugee death toll in Europe creates an urgent need for novel tools that monitor and forecast refugee flows. This study investigates the correlation between refugee mobility data and Internet search data from Google Trends. Google Trends is a freely accessible tool that provides access to Internet search data by analyzing a sample of all web queries. In our study, we surveyed refugees in Greece (entry point) and in Finland (destination point) to identify what search queries they had used during their travel. Next, we conducted time series analysis on Google search data to investigate whether interest in user-defined search queries correlated with the levels of refugee arrival data recorded by the United Nations High Commissioner for Refugees (UNHCR). Results indicate that the reuse of internet search data considerably improves the predictive power of the models.
Kostakos Panos, Pandya Abhinay, Oussalah Mourad, Hosio Simo, Sattari Arash, Kostakos Vassilis, van Berkel Niels, Breidbach Christoph, Kyriakouli Olga
A4 Article in conference proceedings
Place of publication:
2018 IEEE International Conference on Information Reuse and Integration (IRI)
P. Kostakos et al., “Correlating Refugee Border Crossings with Internet Search Data,” 2018 IEEE International Conference on Information Reuse and Integration (IRI), Salt Lake City, UT, 2018, pp. 264-268. doi: 10.1109/IRI.2018.00048
Read the publication here: