Predicting EU migration trends: merging traditional and social media data

Freedom of movement within the European Union (EU) is a central component of the European Common Market and has contributed significantly to the increase in the number of European migrants both leaving and entering other EU member states. In today's data-driven world, understanding and predicting migrant population numbers is crucial for policymakers, researchers, and organizations involved in migration management. Traditional data sources like registers and surveys provide valuable information but often lag behind real-time events and trends, and rely on measurements in each individual member state. Social media platforms such as X (formerly Twitter), Facebook, and Instagram are rich sources of real-time data that have the potential to complement traditional sources and provide timely insights. We have developed a modeling framework to combine both traditional and new migration data sources to estimate a complete and harmonized series of the number of migrants from each EU member state living in another EU country (and the United Kingdom).

We used data from Facebook’s Advertising Platform, complemented with statistics from Eurostat, the EU Labour Force Survey and census data. Facebook is the largest social networking platform in Europe, with about 450 million users who log on at least once a month and more than 300 million users who log on at least once a day. It provides access to a large amount of anonymous data on the characteristics of its users. We used data about the approximate number of users within an EU member state that fit the description of people who used to live in one country and who now live in another.

Incorporating data from a range of sources allows us to combine the strengths of each data source and generate estimates with uncertainty levels for current levels of migrant stocks in each EU country. The estimates from our model provide a complete picture of level and changes in adult annual origin-destination foreign-born migrant populations within the EU not previously available.

We tested our methodology for the period between 2011 and 2019, and our estimates matched well with the observed data available in the Eurostat database.

Our model's comprehensive estimates of migrant populations within the EU can significantly aid policymakers in making informed decisions about resource allocation and integration programs. Future research could expand this model to include more recent data and additional variables, further enhancing its utility for policy development and assessment.

Reference

Yildiz, D., Wiśniowski, A., Abel, G., Weber, I., Zagheni, E., Gendronneau, C., Hoorens, S. (2024) Integrating Traditional and Social Media Data to Predict Bilateral Migrant Stocks in the European Union International Migration Review DOI: 10.1177/01979183241249969

Note: This article gives the views of the author, and not the position of the IIASA blog, nor of the International Institute for Applied Systems Analysis.