The rapid proliferation of mobile phones and other digital devices provides immense opportunities to observe and understand the rapidly changing structure of communities in developing and conflict-affected states. However, current state-of-the-art computational methods used to analyze such data are notoriously ill-suited to answer basic, fundamental questions in the social science and policy arena. This research program develops new, scalable methods for modeling and studying evolving, societal-scale communities and social networks. The technical focus of our work is on adapting spectral machine learning methods to real-world contexts with dynamic social data. This requires innovation to make existing algorithms more scalable, better suited to hypothesis testing, and appropriate to non-stationary regimes, where community structure changes continuously over time. Our practical focus is on applying these methods to study the impact of significant geopolitical events on the social fabric of micro- and meso-scale community networks in multiple developing countries.
Joshua Blumenstock, Sham Kakade, Jacob Shapiro
Social networks in developing countries
Office of Naval Research