Predicting Political Orientation in News with Latent Discourse Structure to Improve Bias Understanding

Nicolas Devatine (1, 2) , Philippe Muller (1, 2) , Chloé Braud (1, 3)

1 IRIT-MELODI - MEthodes et ingénierie des Langues, des Ontologies et du DIscours
2 UT3 - Université Toulouse III - Paul Sabatier
3 CNRS - Centre National de la Recherche Scientifique

With the growing number of information sources, the problem of media bias becomes worrying for a democratic society. This paper explores the task of predicting the political orientation of news articles, with a goal of analyzing how bias is expressed. We demonstrate that integrating rhetorical dimensions via latent structures over sub-sentential discourse units allows for large improvements, with a +7.4 points difference between the base LSTM model and its discourse-based version, and +3 points improvement over the previous BERT-based stateof-the-art model. We also argue that this gives a new relevant handle for analyzing political bias in news articles.

Domaines: Informatique et langage [cs.CL]

Nicolas Devatine, Philippe Muller, Chloé Braud. Predicting Political Orientation in News with Latent Discourse Structure to Improve Bias Understanding. 3rd Workshop on Computational Approaches to Discourse (CODI 2022), Oct 2022, Gyeongju, South Korea. pp.77-85. ⟨hal-03877859⟩