Community Detection in Philippine Congress Legislators

Abstract

A program that would detect communities of specific sizes in a network of legislators, as well as compute different centralities of each network nodes, have always been a sought tool in the field of political science for the entities in that network play vital roles in our government. The Philippine congress is consists of over 300 house members and 58 standing committees, and it is crucial to look at how these entities work together, with the consideration of their political involvements and relationship. The data used contains political involvements of the 17th Congress of The Philippines. Analyzing these data will result to an output that is not commonly obvious to people. For the analysis, community detection by means of clique-finding algorithms is used. Cluster or communities are extracted, as well as centrality measures of each node, to be able to see whose members have stronger connection towards others. The software also produces a graph visualization of the network and export the results as a PDF file. The software is using Java as its interface and R for some of its functionalities.