\r\nin understanding the structure and function of a social network.

\r\nLouvain algorithm, which is based on Newman-Girman modularity

\r\noptimization technique, is extensively used as a computationally

\r\nefficient method extract the communities in social networks. It

\r\nhas been suggested that the nodes that are in close geographical

\r\nproximity have a higher tendency of forming communities. Variants

\r\nof the Newman-Girman modularity measure such as dist-modularity

\r\ntry to normalize the effect of geographical proximity to extract

\r\ngeographically dispersed communities, at the expense of losing

\r\nthe information about the geographically proximate communities.

\r\nIn this work, we propose a method to extract geographically

\r\ndispersed communities while preserving the information about the

\r\ngeographically proximate communities, by analyzing the ‘community

\r\nnetwork’, where the centroids of communities would be considered as

\r\nnetwork nodes. We suggest that the inter-community link strengths,

\r\nwhich are normalized over the community sizes, may be used

\r\nto identify and extract the ‘overlay communities’. The overlay

\r\ncommunities would have relatively higher link strengths, despite

\r\nbeing relatively apart in their spatial distribution. We apply this

\r\nmethod to the Gowalla online social network, which contains

\r\nthe geographical signatures of its users, and identify the overlay

\r\ncommunities within it.","references":"[1] R. Albert and A.-L. Barab\u00b4asi, \u201cStatistical mechanics of complex\r\nnetworks,\u201d Reviews of Modern Physics, vol. 74, pp. 47\u201397, 2002.\r\n[2] D. Kasthurirathna, A. Dong, M. Piraveenan, and I. Y. Tumer, \u201cThe\r\nfailure tolerance of mechatronic software systems to random and\r\ntargeted attacks,\u201d in ASME 2013 International Design Engineering\r\nTechnical Conferences and Computers and Information in Engineering\r\nConference. American Society of Mechanical Engineers, 2013, pp.\r\nV005T06A036\u2013V005T06A036.\r\n[3] M. Girvan and M. E. Newman, \u201cCommunity structure in social and\r\nbiological networks,\u201d Proceedings of the national academy of sciences,\r\nvol. 99, no. 12, pp. 7821\u20137826, 2002.\r\n[4] M. E. Newman, \u201cThe structure and function of complex networks,\u201d\r\nSIAM review, vol. 45, no. 2, pp. 167\u2013256, 2003.\r\n[5] J. Leskovec, K. J. Lang, A. Dasgupta, and M. W. Mahoney, \u201cStatistical\r\nproperties of community structure in large social and information\r\nnetworks,\u201d in Proceedings of the 17th international conference on World\r\nWide Web. ACM, 2008, pp. 695\u2013704. [6] M. E. Newman, \u201cModularity and community structure in networks,\u201d\r\nProceedings of the national academy of sciences, vol. 103, no. 23, pp.\r\n8577\u20138582, 2006.\r\n[7] P. Shakarian, P. Roos, D. Callahan, and C. Kirk, \u201cMining for\r\ngeographically disperse communities in social networks by leveraging\r\ndistance modularity,\u201d in Proceedings of the 19th ACM SIGKDD\r\ninternational conference on Knowledge discovery and data mining.\r\nACM, 2013, pp. 1402\u20131409.\r\n[8] M. G. Herander and L. A. Saavedra, \u201cExports and the structure of\r\nimmigrant-based networks: the role of geographic proximity,\u201d Review\r\nof Economics and Statistics, vol. 87, no. 2, pp. 323\u2013335, 2005.\r\n[9] R. Medina and G. Hepner, Geospatial analysis of dynamic terrorist\r\nnetworks. Springer, 2008.\r\n[10] V. D. Blondel, J.-L. Guillaume, R. Lambiotte, and E. Lefebvre, \u201cFast\r\nunfolding of communities in large networks,\u201d Journal of statistical\r\nmechanics: theory and experiment, vol. 2008, no. 10, p. P10008, 2008.\r\n[11] P. Expert, T. S. Evans, V. D. Blondel, and R. Lambiotte, \u201cUncovering\r\nspace-independent communities in spatial networks,\u201d Proceedings of the\r\nNational Academy of Sciences, vol. 108, no. 19, pp. 7663\u20137668, 2011.\r\n[12] J. Hannigan, G. Hernandez, R. M. Medina, P. Roos, and P. Shakarian,\r\n\u201cMining for spatially-near communities in geo-located social networks,\u201d\r\narXiv preprint arXiv:1309.2900, 2013.\r\n[13] X. Liu, T. Murata, and K. Wakita, \u201cExtracting the multilevel\r\ncommunities based on network structural and nonstructural information,\u201d\r\nin Proceedings of the 22nd international conference on World Wide\r\nWeb companion. International World Wide Web Conferences Steering\r\nCommittee, 2013, pp. 191\u2013192.\r\n[14] K. Aberer, L. O. Alima, A. Ghodsi, S. Girdzijauskas, S. Haridi, and\r\nM. Hauswirth, \u201cThe essence of p2p: a reference architecture for overlay\r\nnetworks,\u201d in Peer-to-Peer Computing, 2005. P2P 2005. Fifth IEEE\r\nInternational Conference on. IEEE, 2005, pp. 11\u201320.\r\n[15] J. Leskovec and A. Krevl, \u201c{SNAP Datasets}:{Stanford} large network\r\ndataset collection,\u201d 2014.\r\n[16] R. Albert, H. Jeong, and A.-L. Barab\u00b4asi, \u201cError and attack tolerance of\r\ncomplex networks,\u201d nature, vol. 406, no. 6794, pp. 378\u2013382, 2000.\r\n[17] M. E. J. Newman, \u201cMixing patterns in networks,\u201d Physical Review E,\r\nvol. 67, no. 2, p. 026126, 2003.\r\n[18] Lirneasia. (Online). Available: http:\/\/www.lirneasia.net","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 121, 2017"}