Method for mining key users in social networks

Abstract

The present invention relates to a method for mining key users in social networks. The method comprises: a. calculating the authority of introducing a website by using an Au-PageRank algorithm; b. calculating the probability that a user browses a page in the next step by using a 2S-PageRank algorithm; and c. combining the authority obtained in step a with the probability of page browsing obtained in step b, so that the user take one more step while further surfing the internet, the Au-2S-PageRank algorithm is obtained, and the ranking result is generated through the Au-2S-PageRank algorithm. According to the method for mining key users in social networks provided by the present invention, the Au-PageRank algorithm is combined with the 2S-PageRank algorithm to form the Au-2S-PageRank algorithm, so that the effect of the classical PageRank algorithm on the result due to the average allocation weight is solved, the convergence speed can be accelerated when calculating, and the ranking result is more accurate.

Description

technical field [0001] The invention relates to the field of social network information algorithms, in particular to a mining method for key users of a social network. Background technique [0002] A social network is a social structure composed of individuals and groups connected by one or more factors. The Internet space provides great feasibility for users to generate new social methods. In 1960, the concept of social network was first proposed at the University of Illinois in the United States. After that, the first social networking site, "Six Degrees.com", was established. After 2002, various social networking sites such as LinkIn blossomed everywhere, bringing a major revolution to this field and greatly enriching social networks. Today, social networking is hugely popular, providing users with a plethora of communication tools. Whether it is the joining of new members or the establishment of new connections between members, the entire social network will grow, an...

AI Technical Summary

Problems solved by technology

[0010] The technical problem to be solved by the present invention is: aiming at the shortcomings of the classic PageRank algorithm to distribute weights equally, each node is given a corresponding degree of authority when performing weight distribution, and referring to the actual operation of the user, the simulation user can browse the webpage according to the Subjective intention to select the next step, thus effectively filtering the noise information in the network, providing a mining method for key users of social networks, and solving the impact of the classic PageRank algorithm on the results due to the average distribution of weights

Images