Key path extraction method of propagation network

Abstract

The invention discloses a key path extraction method of the propagation network. An extra node is added to the propagation network, and bidirectional connection with each node of the propagation network is further established; the node similarity between any two nodes of the extra node propagation network is calculated; a node influence column vector is initialized based on the total quantity of the nodes of the extra node propagation network, a probability transfer matrix is further established, and global voting iteration is carried out to update the node influence column vector; traversal elimination of shortest paths of any two user nodes of the extra node propagation network is carried out, a path node influence row vector and a path node similarity row vector are established for eachshortest path; the comprehensive path influence of each shortest path is acquired through calculation to order each shortest path to acquire a key path. The method is advantaged in that a problem inmining the key propagation path on a social network platform is solved, and the method can be applied to the network information monitoring fields for public opinion monitoring and intervention and rumor detection.

Description

technical field [0001] The invention belongs to the field of network information mining, and relates to a key path extraction method of a communication network. Background technique [0002] In recent years, the vigorous development of social platforms has brought about a large number of information supervision problems, especially in the field of public opinion control and intervention. In addition to discovering the key nodes in the social network, that is, the opinion leaders who guide the direction of public opinion, it is also very important to mine the communication paths between these nodes. Most of the research at this stage focuses on the identification of key nodes and the characteristic analysis of the path, and there is little in-depth mining of the key path of its propagation, which will make it particularly difficult to search for public opinion and the propagation path of rumor detection. Contents of the invention [0003] In order to solve the problem of m...

AI Technical Summary

Problems solved by technology

Most of the research at this stage focuses on the identification of key nodes and the feature analysis of paths, and there is little in-depth mining of the key paths of its propagation, which will make it particularly difficult to search for public opinion and spread paths for rumor detection

Images