Discovering and characterizing political elite cliques with evolutionary community detection

Abstract

Among many real-world applications of social network analysis, political power interaction and executive succession show unique characteristics of dynamic community evolution and raise interesting research challenges. Interactions of political power among community members are mostly subtle and behind the scene. Visible relations are only nominal and are not readily apparent to key findings. Under such circumstances of information deficiency, the research problem is to uncover the inner relations among some of the network entities and to discover hidden network structures based on these inner relations. In this research, our objective is to identify the inner circles of government political power holders underneath formal work relations and observe how the political elite groups form and change over time. We propose a model of government elite clique evolution in which synchronous post assignment and job promotion within a time window are considered as entity relations. In each snapshot of network evolution, communities that exhibit strong association of synchronous job change are identified by the edge betweenness decomposition algorithm. Then, an event-based framework is used to characterize community behavior patterns in consecutive changes of network structures. The approach is effectually demonstrated on two scenarios: (1) identifying and tracking the inner circle of a political leader; (2) finding succession pool members in government agencies. We further suggest two evolutionary community variation indexes to assess political executive succession. Experimental results with actual government personnel data provide evidence that government agency succession can be reasonably measured to reflect its overall tendency of personnel promotion. This work also has the practical value of providing objective scrutiny on political power transition for the benefit of public interest.