Visualizing Media Bias through Twitter
DOI:
https://doi.org/10.1609/icwsm.v6i2.14343Keywords:
news media, social media, media bias, social network analysisAbstract
Traditional media outlets are known to report political news in a biased way, potentially affecting the political beliefs of the audience and even altering their voting behaviors. Therefore, tracking bias in everyday news and building a platform where people can receive balanced news information is important. We propose a model that maps the news media sources along a dimensional dichotomous political spectrum using the co-subscriptions relationships inferred by Twitter links. By analyzing 7 million follow links, we show that the political dichotomy naturally arises on Twitter when we only consider direct media subscription. Furthermore, we demonstrate a real-time Twitter-based application that visualizes an ideological map of various media sources.