The digitalization and globalization of our news channels have had a profound impact on worldwide information diffusion. Nowadays, information is processed in mass by large organizational structures, before being propagated to local channels. This process often obfuscates the origin of a news story, blurs the accountability chain to the author of its coverage, and reduces the traceability to its inception.
This work proposes a model of the media landscape that automatically maps news sources based on their selection of subjects.
By tracking sources’ evolution over time, driving forces are identified, from the influence of ownership to large-scale content diffusion patterns.
A dynamic map of the media landscape over the last 3 years has been produced, based on coverage from 500M articles shared by around 8K sources.