Ranking nodes by silentness

Silentness in networks refers to the behavior that a node receives lots of information from other nodes but share nothing or little information with them. We can rank people in social networks by silentness. In this paper we present an algorithm based on random walks for ranking nodes by silentness. The time complexity of the proposed algorithm in a network with n nodes is O(log2n) with high probability, while the state-of-the-art algorithm does not specified time complexity and runs until holds convergence conditions and we show it does not converge in all cases by a counterexample. We assess the proposed algorithm with Fagin's intersection metric and Bperef methods and compare the implementation results of the algorithm on GPlus and Twitter datasets with PageRank and I/O ranking methods. We implement our algorithm on Hadoop framework, as well and in compare of the state-of-the-art algorithm reduces 64.48% of the disk I/O.