Power Law Distribution Of Encyclopedia Entry And Network Structure Study

In recent years,complex networks have attracted extensive attention from scholars in various disciplines,including sociology,statistical physics,biology and statistical.Scale-free network can show the real world more vividly.The degree distribution of scale-free network is subject to power law distribution,and power law distribution widely exists in all aspects of nature and life,and Hub nodes in scale-free network play a crucial role in network structure and function.Therefore,the study of scale-free phenomena is helpful to understand the nature of different phenomena in real life.In this paper we study the following two parts:Firstly,we collect the editing history data of encyclopedia including featured entries and general entries,and analyze the two groups of entries from two aspects:the whole editing history time interval and the user editing history time interval.We use the maximum likelihood estimation method to estimate parameters and the likelihood ratio test to test results.The results show that the whole editing history time interval distribution of feature entries follows the double power law.The parameters of the first half are approximately equal to 1.1,and the parameters of the second half are all greater than 2.The user edit history time interval follows the single power law with the parameter approximately equaling to 1.1.The whole editing history time interval distribution of general entries follows the single power law,and the parameter is approximately equal to 1.1.The user edit history time interval obeys the single power law,and the parameter is approximately equal to 1.1.Secondly,we focus on the structure learning problem of the hub network.In the neighborhood selection framework,we use the ₁L and ₂L regularizers to incorporate the sparse and group prior of the hub network.We employ the coordinate descent algorithm to solve the resulting model.Simulation and real data analysis show that the proposed method is effective and applicable.