Uncovering gender bias in newspaper coverage of Irish politicians using machine learning

Abstract

This article presents a text-analytic approach to analysing media content for evidence of gender bias. Irish newspaper content is examined using machine learning and natural language processing techniques. Systematic differences in the coverage of male and female politicians are uncovered, and these differences are analysed for evidence of gender bias. A corpus of newspaper coverage of politicians over a 15-year period was created. Features of the text were extracted and patterns differentiating coverage of male and female politicians were identified using machine learning. Discriminative features were then analysed for evidence of gender bias. Findings showed evidence of gender bias in how female politicians were portrayed, the policies they were associated with, and how they were evaluated. This research also sets out a methodology whereby natural language processing and machine learning can be used to identify gender bias in media coverage of politicians.