A link-based approach to detect media bias in news websites

Abstract

News websites are currently one of the main sources of information. Like traditional media, these sources can have a bias in how they report news. This media bias can influence how people perceive events, political decisions, or discussions. In this paper, we describe a link-based approach to identify news websites with the same political orientation, i.e., characterize the bias of news websites, using network analysis techniques. After constructing a graph from a few seeds with previously known bias, we show that a community detection algorithm can identify groups formed by sources with the same political orientation.