Affiliations: School of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA 6009, Australia. E-mails: kwanhui@graduate.uwa.edu.au, datta@csse.uwa.edu.au
Correspondence:
[*]
Corresponding author. K.H. Lim is now with the Department of Computing and Information Systems, University of Melbourne, Australia. E-mail: limk2@student.unimelb.edu.au.
Abstract: The immense popularity and rapid growth of Online Social Networks (OSN) have attracted the interest of researchers and companies, particularly in how users group together to form communities online. While many community detection algorithms have been developed to detect communities on such OSNs, most of these algorithms are based only on topological links and researchers have observed that many topological links do not translate to actual user interaction. As such, many members of the detected communities do not communicate frequently to each other. This inactivity creates a problem in targeted advertising and viral marketing, which require the community to be highly active so as to facilitate the diffusion of product/service information. We propose an approach to detect highly interactive Twitter communities that share common interests, based on the frequency and patterns of direct tweeting among users, rather than the topological information implicit in follower/following links. Our experimental results show that communities detected by our proposed approach are more cohesive and connected within different interest groups, based on topological measures. We also show that the detected communities actively interact about the specific interests, based on the high frequency of #hashtags and @mentions related to this interest. In addition, we study the trends in their tweeting patterns such as how they follow and unfollow other users, and observe that our approach detects communities comprising users whose links are more persistent compared to those in other groups of users.
Keywords: Twitter, tweets, social network analysis, community detection, like-minded communities, interaction links, common interests
