That is from the paper by An et al (2012), "Twitter follow links reveal bicameral landscape of newspapers." The authors explain:
This paper presented a first-of-its-kind, although preliminary study of the political media landscape of Twitter. We proposed a novel algorithm that generates a political di- chotomy map of media sources on Twitter, which is based on gathering online data and aggregating it via a closeness measure, without any complex procedures unlike in the past. Furthermore the ideological map of a particular issue can be created in real time in conjunction with a public stream of tweets from Twitter. Extending this work, we are currently examining how news media sources of different po- litical slants cover the same news story by conducting topic classification on news articles that are shared on Twitter.
We observed that the political dichotomy naturally arises on Twitter when we only consider direct media subscription. It implies that Twitter user may live in political echo-chamber. It is said that individuals need to have access to a pool of multiple points of view against which they can contrast their own values and belief as it helps them shape their eventual opinion. Nonetheless, we deemphasize the potential benefit of such political diversity because not ev- eryone prefers to receive diverse political opinions (Munson and Resnick 2010). Hence different strategies are required to assist heterogeneous individuals when news aggregators plan to increase opinion diversity. We hope to build a real- time platform that helps people receive balanced news information based on the proposed model that tracks bias in news in the future.
Important paper, innovative method, and numberless possibilities of applications and replications.