Gender bias recognition in political news articles

Abstract

Gender bias exists not only in the stereotypes used to portray male and female figures, but more importantly, in the word choice media outlets use to describe political figures. Research in computational linguistics has not yet focused on the problem of identifying gender bias in political news from a variety of leanings, despite decades of research from the political science perspective. In this work, we introduce a new dataset – News-Bias – and demonstrate through extensive experimentation that there exists significant gender bias in political news, even with all gendered terms, and personally identifiable information removed. We show that bias persists through the document embeddings, sentiment and word choice across news outlets and political leanings.