Mapping Subnational Gender Gaps in Internet and Mobile Adoption Using Social Media Data

Casey Breen, University of Oxford
Masoomali Fatehkia, Qatar Computing Research Institute
Xinyi Zhao, Max Planck Institute for Demographic Research (MPIDR) /University of Oxford
Jiani Yan, University of Oxford
Douglas R Leasure, Leverhulme Centre for Demographic Science, Department of Sociology, University of Oxford
Ingmar Weber, Saarland University
Ridhi Kashyap, University of Oxford

The digital revolution has ushered in tremendous societal and economic benefits. Yet access to digital technologies such as mobile phones and internet remains highly unequal, especially by gender in the context of LMICs. Reliable, quantitative estimates of digital gender inequalities are essential for monitoring gaps and implementing targeted interventions within the global sustainable development goals. We develop estimates of internet and mobile adoption by gender and digital gender gaps at the subnational level for 874 regions in 55 countries across the African continent. We construct these estimates by applying machine-learning algorithms to Facebook audience counts derived from the platform’s marketing application programming interface (API), geospatial and population data. We train and assess the performance of these algorithms using “ground truth” data from the Demographic and Health Surveys from 19 countries in Africa. Our results reveal striking disparities in access to digital technologies, with implications for policy formulation and infrastructure investment.