%0 Journal Article
	%A Madhushi Bandara and  Dharshana Kasthurirathna and  Danaja Maldeniya and  Mahendra Piraveenan
	%D 2017
	%J International Journal of Computer and Information Engineering
	%B World Academy of Science, Engineering and Technology
	%I Open Science Index 121, 2017
	%T Detecting Geographically Dispersed Overlay Communities Using Community Networks
	%U https://publications.waset.org/pdf/10006271
	%V 121
	%X Community detection is an extremely useful technique
in understanding the structure and function of a social network.
Louvain algorithm, which is based on Newman-Girman modularity
optimization technique, is extensively used as a computationally
efficient method extract the communities in social networks. It
has been suggested that the nodes that are in close geographical
proximity have a higher tendency of forming communities. Variants
of the Newman-Girman modularity measure such as dist-modularity
try to normalize the effect of geographical proximity to extract
geographically dispersed communities, at the expense of losing
the information about the geographically proximate communities.
In this work, we propose a method to extract geographically
dispersed communities while preserving the information about the
geographically proximate communities, by analyzing the ‘community
network’, where the centroids of communities would be considered as
network nodes. We suggest that the inter-community link strengths,
which are normalized over the community sizes, may be used
to identify and extract the ‘overlay communities’. The overlay
communities would have relatively higher link strengths, despite
being relatively apart in their spatial distribution. We apply this
method to the Gowalla online social network, which contains
the geographical signatures of its users, and identify the overlay
communities within it.
	%P 80 - 85