Machine-Learning media bias

Abstract

We present an automated method for measuring media bias. Inferring which newspaper published a given article, based only on the frequencies with which it uses different phrases, leads to a conditional probability distribution whose analysis lets us automatically map newspapers and phrases into a bias space. By analyzing roughly a million articles from roughly a hundred newspapers for bias in dozens of news topics, our method maps newspapers into a two-dimensional bias landscape that agrees well with previous bias classifications based on human judgement. One dimension can be interpreted as traditional left-right bias, the other as establishment bias. This means that although news bias is inherently political, its measurement need not be.

Data Driven Model to Investigate Political Bias in Mainstream Media

“…Another study worth mentioning by D'Alonzo and Tegmark [36] investigates media bias by using a combination of machine learning and Principal Component Analysis (PCA) paired with Single Value Decomposition (SVD) to understand how bias affected different news outlets. Their approach of topic-specific n-gram lists to create predictive models was the inspiration of our study as well.…”

“…Moreover, the majority of research also relied heavily on outside datasets to do their analysis: Tran [35] used EveryPolitician, the Wikipedia API, Political-related Articles Collection datasets, and API's in his analysis. D'Alonzo and Tegmark [36] used the Swiss Policy Research Media Navigator classification to determine how pro-establishment a news outlet is. The data collection regime in these thirdparty datasets is unclear to us.…”