The aim of this study was to develop a tool to 'nowcast' migrant stocks by using real-time data from the Facebook Marketing Application Programming Interface (API) and official migration data from EU member states and states in the United States. The tool produces real-time nowcasts which can serve as an early-warning system for decision-makers to anticipate 'shock events' and rapid migration trends, and make evidence-based policy decisions.

Cover: Using social media data to 'nowcast' international migration around the globe
Read Online

Using social media data to 'nowcast' international migration around the globe

by Andreas Culora, Emma Thomas, Eliane Dufresne, Matthew Cefalu, Clement Fays, Stijn Hoorens

Download eBook for Free

FormatFile SizeNotes
PDF file 7.2 MB

Use Adobe Acrobat Reader version 10 or higher for the best experience.

Research Question

  1. Can real-time proxy migrant stocks data from the Facebook Marketing API be combined with migrant stocks data from official data sources using a Bayesian modelling approach to nowcast stocks of migrants in EU member states and US states?

The aim of this study was to develop a methodological tool to 'nowcast' migrant stocks by using real-time data from the Facebook Marketing Application Programming Interface (API) and official migration data from EU member states and states in the United States. To meet this aim, RAND researchers collected real-time data that could provide estimates of migrant stocks in the countries of interest from the Facebook Marketing API, along with migrant-stocks data from official sources from 2010 onwards, and developed a Bayesian model capable of combining the Facebook and official migration data to nowcast stocks of migrants in EU member states and US states. The model developed in this study is capable of producing near real-time nowcasts for each source of official statistics, which can serve as an early-warning system to anticipate 'shock events' and rapid migration trends that would otherwise be captured too late or not at all by official migration data sources. This tool therefore enables decision-makers to make informed, evidence-based policy decisions in the rapidly changing social policy sphere of international migration. The study also provides a useful example of how to combine 'big data' with traditional data to improve measurement and estimation which can be applied to other social and demographic phenomena. Suggestions for future work include continued data collection activities to extend the temporal overlap between Facebook data and official migration statistics, nowcasting migrant stocks for demographic subgroups, and exploring alternative specifications for the Bayesian model to improve the accuracy of the nowcasts.

Recommendations

  • Continue the data collection to extend the temporal overlap between social media and the official migration data sources and maximise the accuracy of the nowcasts.
  • Compare the performance of the model developed in this study with other approaches to nowcasting migrant stocks.
  • Develop an interactive tool to analyse and visualise the nowcasts geo-spatially to identify sudden and dramatic changes in the migrant stock estimates and define early-warning signals.
  • Nowcast migrant stocks for specific demographic subgroups, such as men and women separately, children and young people, etc.
  • Explore alternative specifications for the Bayesian model to improve the accuracy of the nowcasts.

Table of Contents

  • Chapter One

    Introduction

  • Chapter Two

    Traditional and new data to estimate international migrant stocks

  • Chapter Three

    Data sources for international migrant stock estimates

  • Chapter Four

    Methodology to nowcast international migration

  • Chapter Five

    Migrant stock nowcasting results

  • Chapter Six

    Concluding remarks

  • Annex A

    Migration data annual time series

  • Annex B

    Facebook Marketing API data monthly time series

  • Annex C

    Example data

  • Annex D

    Detailed description of all official data sources collected

  • Annex E

    Lists of corridor clusters

Research conducted by

Funding for this research was provided by gifts from RAND supporters and income from operations. This research was conducted by RAND Europe.

This report is part of the RAND Corporation Research report series. RAND reports present research findings and objective analysis that address the challenges facing the public and private sectors. All RAND reports undergo rigorous peer review to ensure high standards for research quality and objectivity.

This document and trademark(s) contained herein are protected by law. This representation of RAND intellectual property is provided for noncommercial use only. Unauthorized posting of this publication online is prohibited; linking directly to this product page is encouraged. Permission is required from RAND to reproduce, or reuse in another form, any of its research documents for commercial purposes. For information on reprint and reuse permissions, please visit www.rand.org/pubs/permissions.

The RAND Corporation is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.