Reconstructing news spread networks and studying its dynamics

Abstract

News spread can be seen as a contagious process in internet media outlets. This process can be transformed into a temporal network which represents the influence between published articles and between media outlets. In this article, we propose a methodology based on the application of natural language analysis of the articles to reconstruct the latent network through which news spread. From the reconstructed network, we analyze the network dynamic and then show that the dynamics of the news spread can be approximated by a classical SIR epidemiological dynamic upon the network. From the results obtained we argue that the methodology proposed can be used to make predictions about media repercussion, and also to detect viral news in news streams.