DETECTION AND EVALUATION OF COMMUNITY STRUCTURES IN SOCIAL NETWORKS
Open Access
Author:
Ghurye, Akshay Dattatraya
Graduate Program:
Industrial Engineering
Degree:
Master of Science
Document Type:
Master Thesis
Date of Defense:
None
Committee Members:
Soundar Kumara, Thesis Advisor/Co-Advisor Soundar R. T. Kumara, Thesis Advisor/Co-Advisor
Keywords:
parallel programming community detection overlapping social networks complexity
Abstract:
In today's world, social media networks capture interactions among people through comments on blogs, posts and feeds. The public availability of these networks has allowed researchers and businesses alike to delve more into these preferences so as to extract communities which clearly define their formation. In social networks, people tend to have more than one preference over different products which makes it difficult to put them in a single community. Although community detection has been well applied to social networks, not much work has been done in detecting overlapping communities within these networks. In this paper we describe an algorithm which applies a game theoretic approach to graph clustering to determine overlapping communities within complex networks and also show how a parallel implementation of the algorithm can be used to detect communities in lesser time than its previous implementations. Further we run the algorithm on various social networks to detect overlapping communities and propose a method to analyze them once they are determined. We conclude by providing impetus on the running time of this algorithm and expressing the need for faster algorithms to detect and analyze social media networks.