TFRank: An Evaluation of Users Importance with Fractal Views in Social Networks

Authors: Fei Hao, Hai Wang

Abstract:

One of research issues in social network analysis is to evaluate the position/importance of users in social networks. As the information diffusion in social network is evolving, it seems difficult to evaluate the importance of users using traditional approaches. In this paper, we propose an evaluation approach for user importance with fractal view in social networks. In this approach, the global importance (Fractal Importance) and the local importance (Topological Importance) of nodes are considered. The basic idea is that the bigger the product of fractal importance and topological importance of a node is, the more important of the node is. We devise the algorithm called TFRank corresponding to the proposed approach. Finally, we evaluate TFRank by experiments. Experimental results demonstrate our TFRank has the high correlations with PageRank algorithm and potential ranking algorithm, and it shows the effectiveness and advantages of our approach.

Keywords: TFRank, Fractal Importance, Topological Importance, Social Network

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1334457

References:

[1] N. He, W. Y. Gan, D. Y. Li, Evaluate nodes importance in the network using data field thoery, 2007 International Conference on Convergence Information Technology, pp.1225-1230, 2007.
[2] Freeman L. C. Centrality in social networks: I. Conceptual clarification, Social Networks, 1, pp.215-239, 1979.
[3] K. Musial, P. Kazienko, P. Brodka, User position measures in social networks, The 3rd SNA-KDD Workshop, 2009.
[4] S. Brin and L. Page, The anatomy of a large-scale hypertextual web search engine, Computer Networks, 30, pp.107-117, 1998.
[5] Jon M. Kleinberg. Authoritative sources in a hyperlinked environment. Journal of the ACM, 46(5), 1999.
[6] Y. S. Han, L. Y Kim, J. W. Cha, Evaluation of user reputation on YouTube, LNCS 5621, pp.346-353, 2009.
[7] C. C. Yang, M. Sageman, Analysis of terrorist social networks with fractal views, Journal of Information Science, 35(3), pp.299-320, 2009.
[8] H. Koike, Fractal views: a fractal-based method for controlling information display, ACM Transactions on Information Systems 13(3), 1995.
[9] H. Koike and H. Yoshihara, Fractal approaches for visualizing huge hierarchies. In: Proceedings of IEEE Symposium on Visual Laugnagues, 1993.
[10] J. Xu and H. Chen, Fighting organized crimes: using shortest-path algorithms to identify associations in criminal networks, Decision Support Systems, 38, pp.473-487, 2003.