IMPROVED COMMUNITY DETECTION ALGORITHM BASED ON DISTANCE CENTRALITY IN SOCIAL NETWORK

Computer Engineering

In today's era, online social networks have become quite prominent, and a lot of research is getting done for making these networks useful and more enjoyable, by suggesting useful communities and similar interest communities to users. Also due to freely available web space and interactions, there are multi communities per user, making it really hard for highly iterative algorithms to perform fast and give meaningful suggestions. So, using community detection algorithm provides some important information from social network. Social network is one of the most vital complicated networks. Many existing community detection algorithms are developed. Distance Centrality based Community Detection algorithm required the more recalculations of center node for each community. In this paper, we propose improved Distance Centrality based Community Detection algorithm which reduce the recalculations of center node for each community. First we calculate the distance between nodes and get the pre-community then choose the center node by calculating the closeness centrality of each node using their distance data. Then check the similarity between pre-community nodes and non pre-community nodes and assign every node to the foremost similar community. We will get communities from the social network. We demonstrate that the proposed improved Distance Centrality based Community Detection (iDCCD) algorithm terminated on a decent community number and additionally has comparable detection accuracy with different existing approaches.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.