Slanted news coverage has long been studied in the socialsciences, resulting in comprehensive models to describe it and effective yetcostly methods to analyze it . We present anin-progress system for news recommendation that is the first to automate themanual procedure of content analysis to reveal person-targeting biases in news articles reporting on policy issues . The study shows that recommending news articles that differently framean event significantly improves respondents’ awareness of bias. It also shows that recommendation articles that . differently frame an event significantly improve respondents’ awareness of . bias. The study was conducted in a large-scale user study, we find verypromising results regarding this interdisciplinary research direction. Ourrecommender detects and reveals substantial frames that are actually present in .

Author(s) : Felix Hamborg, Timo Spinde, Kim Heinser, Karsten Donnay, Bela Gipp

Links : PDF - Abstract

Code :

Keywords : news - study - bias - articles - present -

Leave a Reply

Your email address will not be published. Required fields are marked *