that in the worst case the algorithm have the same [9] R. Albert and AL Barabasi. 200 Topology of networks. performance, and that the combined clustering indexes with ts and universality. Phys. Rev. Let. 85. 5234-5237, 2000 the adaptive feature of the Genetic Algorithm is responsible [101 Goldberg. David E. Genetic Algorithms in Search Optimization and for the improved performance. The experiments results achine Learning. Addison Wesley (1989). showed to be very promising: however it is still necessary to lm coye to invite into your social network. Proc. IUI pp. 77-86. 200 9 Ronen L. and wilcox E. Do you know? Recommend apply this algorithm in networks much larger in size and activity. Several papers [1], [2], [3], [4] and [7) have [12 Chen, J, Geyer, W, Dugan, C. and Guy, I Make new friends,but investigated the topological structure of SNSs and others H,pp.201-210.2009 complex networks. However, we have showed that these analyses can be used to develop some practical applications [13] Liben-Nowell, D, and Kleinberg, J. The link pre social networks. Proceedings of the twelfth intemational in the field of recommendation system. on Information and knowledge management, pp 556-559. For future work, it is important to test the proposed [14] R Bell, Y Koren, C Volinsky(2008)."The BellKor solution to the mechanism more intensively in a larger network using Netflix Prize 2008 several test groups. In addition, this approach based on http://www.netflixprize.com/assets/progressprize2008_beLlkor.pdf network topology can be also used for other type of ecommendation networks system apart from SNSs. An example is the innumerous e-commerce systems that constitute bipartite networks composed by users and products and could be mapped as single entity graphs e would like to acknowledge the recife center for Advanced Studies and Systems(C.E.S. A R) for providing the Oro-Aro database In particular we would like to thanks Ricardo Araujo Costa for assistance in managing the database information. Also, FACEPE Fundacao de Amparo a Ciencia e Tecnologia do estado de Pernambuco, for financial support. [1] Mislove, A, Marcon, M, Gummadi, K. Networks. Proceedings of the 7th ACM SIGCOMM Conference on Internet Measurement (San Diego, California, USA. October 24-26, 2007). IMC07. ACM Press, New York, NY, 29-42. 2] Ahn Y.Y. Han, S, Kwak, H, Moon, S. and Topological Characteristics of Huge Online Services. Proceeding of the 16th Intemationa Wide Web Conference, (Banff, Alberta, Canada, May 8-12, 2007).Www'07 ACM Press, New York, NY, 835-844. 2007. [3] Wilson, M, and Nicholas, C. Topological Analysis of an Online ocial Network for older Adults. Proceeding of the 2008 ACm October 30, 2008). SSM08. ACM Press. New York, NY, 51-58 M1008甲1B12时1时2 tz, S. D. An Introduction to Structural Analy ork Approach to Social Research. Toronto: Butterwort. 1982 6 Chau, D. H, Pandit, s. Wang, S, and Faloutsos. C, Parallel Crawling for Online Social Networks. Proceedings of the 16th international conference on World wide Web(Banff, Alberta Canada, May 8-12, 2007).Www'07. ACM Press, New York, NY, 1283-1284. 2007 [7 Kumar, R, Novak, J, and Tomkins, A. Structure and Evolution of 8] Karrer. B, Levina. E. and Newman. M. EJ. 2008. Robustness of ommunity structure in networks. Phys Rev. E77046119, 2008that in the worst case the algorithm have the same performance, and that the combined clustering indexes with the adaptive feature of the Genetic Algorithm is responsible for the improved performance. The experiments results showed to be very promising; however it is still necessary to apply this algorithm in networks much larger in size and activity. Several papers [1], [2], [3], [4] and [7] have investigated the topological structure of SNSs and others complex networks. However, we have showed that these analyses can be used to develop some practical applications in the field of recommendation system. For future work, it is important to test the proposed mechanism more intensively in a larger network using several test groups. In addition, this approach based on network topology can be also used for other type of recommendation networks system apart from SNSs. An example is the innumerous e-commerce systems that constitute bipartite networks composed by users and products and could be mapped as single entity graphs. ACKNOWLEDGMENT We would like to acknowledge the Recife Center for Advanced Studies and Systems (C.E.S.A.R) for providing the Oro-Aro database. In particular we would like to thanks Ricardo Araújo Costa for assistance in managing the database information. Also, FACEPE – Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco, for financial support. REFERENCES [1] Mislove, A., Marcon, M., Gummadi, K. P., Druschel, P., and Bhattacherjee, B. Measurement and Analysis of Online Social Networks. Proceedings of the 7th ACM SIGCOMM Conference on Internet Measurement. (San Diego, California, USA. October 24-26, 2007). IMC’07. ACM Press, New York, NY, 29 - 42. [2] Ahn,Y.Y., Han,S., Kwak, H., Moon, S., and Jeong, H. Analysis of Topological Characteristics of Huge Online Social Networking Services. Proceeding of the 16th International World Wide Web Conference, (Banff, Alberta, Canada, May 8-12, 2007).WWW '07. ACM Press, New York, NY, 835-844, 2007. [3] Wilson, M., and Nicholas, C. Topological Analysis of an Online Social Network for Older Adults. Proceeding of the 2008 ACM workshop on Search in Social Media. Napa Valley, California, USA, October 30, 2008). SSM’08. ACM Press, New York, NY, 51-58, 2008. [4] Mitchell, M. Complex Systems: Network Thinking. Artificial Intelligence, 170(18), pp. 1194-1212, 2006. [5] Berkowitz, S. D. An Introduction to Structural Analysis: The Network Approach to Social Research. Toronto: Butterwort, 1982 [6] Chau, D. H., Pandit, S., Wang, S., and Faloutsos, C., Parallel Crawling for Online Social Networks. Proceedings of the 16th international conference on World Wide Web. (Banff, Alberta, Canada, May 8-12, 2007).WWW '07. ACM Press, New York, NY, 1283 – 1284, 2007. [7] Kumar, R., Novak, J., and Tomkins, A. Structure and Evolution of Online Social Networks. Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining. (Philadelphia, PA, USA, August 20-23, 2006). KDD’06. ACM Press, New York, NY, 611 – 617. 2006. [8] Karrer, B., Levina, E., and Newman, M.E.J. 2008. Robustness of community structure in networks. Phys Rev. E 77 046119, 2008. [9] R. Albert and A.-L. Barabási. 200. Topology of complex networks: Local events and universality. Phys. Rev. Let. 85, 5234-5237, 2000. [10] Goldberg, David E. Genetic Algorithms in Search Optimization and Machine Learning. Addison Wesley (1989). [11] Guy, I., Ronen I., and Wilcox E. Do you know? Recommending people to invite into your social network. Proc. IUI pp. 77-86. 2009. [12] Chen, J., Geyer, W., Dugan, C., and Guy, I. Make new friends, but keep the old: recommending people on social networking sites. Proc. CHI, pp. 201-210. 2009. [13] Liben-Nowell, D., and Kleinberg, J. The link prediction problem for social networks. Proceedings of the twelfth international conference on Information and knowledge management, pp 556-559. 2003. [14] R. Bell, Y. Koren, C. Volinsky (2008). "The BellKor solution to the Netflix Prize 2008". http://www.netflixprize.com/assets/ProgressPrize2008_BellKor.pdf 239