Knowledge based Community Detection in Online Social Network

In this paper a hierarchy of knowledge community detection is proposed which is able to identify most impactful topics from a Twitter stream, analyze and generate a social network leading to the formation of knowledge-based communities. Data is crawled, in a region-specific manner, to ensure, cohesiveness of content. An aggregated score consisting of a sentiment score(in the range of [-1,1]) and an outreach score is assigned to each tweet, following which the knowledge network is generated, based on the score-wise proximity of tweets. Three community detection algorithms, Leading Eigenvector, Fast Greedy and Walktrap are used to detect communities from the derived knowledge network. Their efficiencies are compared on the basis of the number of communities generated and the modularity. Quality benchmark evaluation to test the network partition is applied for analysing and finally the impact of trending topics on the social stream is measured.