Structural inference in political science datasets

Abstract

Sociopolitical databases provide a rich source of high-dimensional data with hidden spatial-temporal structure; for example countries voting for/against certain UN resolutions is a manifestation of the underlying political alignment among nations. We introduce the notion of diffusion distance as a natural measure in such datasets. and applied diffusion maps to databases of intergovernmental organizations' memberships and UN roll calls. Examination of the embeddings from these data across time reveals interesting historical narratives, suggesting the results serve as a proxy for analysis of security and terrorism datasets.