Core Method for Community Detection

摘要

The processing of networks of interacting objects makes it possible to solve topical issues in the modern world of identifying opinion leaders and channels for the dissemination and exchange of information. In this work, the structure of networks of interacting objects and their possible analysis with the help of weighted graphs based on the interaction of elements of such networks are considered. At the beginning of the work, a methodology for working with a weighted graph was proposed. It is called by the authors the "core method" and provides an algorithm for the analyst's actions to identify communication groups, opinion leaders and disseminate information in the network. The key concepts of the γ-core of the graph, the interaction coefficients and the density of communities and the core are introduced. In the second part of the work, the main capabilities of the software developed by the authors, which allows the operator to carry out the procedures required for the method, visualize the results and export the obtained data, are presented. The third part shows the application of the "core method" on a weighted graph, based on the data about the coverage of the activities of the Moscow city authorities in the fight against the new coronavirus infection Covid-19 imported from Twitter. This example shows how opinion leaders on a weighted graph can be identified using the core method and the implemented application.