Ego Based Community Detection in Online Social Network

Social network can be represented by a graph, where individual users are represented as nodes/vertices and connections between them are represented as edges of the graph. The classification of people based on their tastes, choices, likes or dislikes are associated with each other, forms a virtual cluster or community. The basis of a better community detection algorithm refers to within the community the interaction will be maximized and with other community the interaction will be minimized. In this paper, we are proposing an ego based community detection algorithm and compared with three most popular hierarchical community detection algorithms, namely edge betweenness, label propagation and walktrap and compare them in terms of modularity, transitivity, average path length and time complexity. A network is formed based on the data collected from a Twitter account, using Node-XL and I-graph and data are processed in R based Hadoop framework.