Hyperpartisan News Detection

Patrick Noyau


Supervised by Luis Espinosa-Anke; Moderated by Dr Daniel J. Finnegan

This is a Natural Language Processing project which addresses hyperpartisanism [1].

Formally, the task is defined as: Given a news article text, decide whether it follows a hyperpartisan argumentation, i.e., whether it exhibits blind, prejudiced, or unreasoning allegiance to one party, faction, cause, or person. The project will use the official data from a recent competition [2]. A strong deliverable should consist of a text categorization system written in Python that works, i.e., produces output that can be evaluated using the official evaluation script; and whose design is the result of well informed data-driven intuitions as well as software engineering best practices.

[1] Potthast, M., Kiesel, J., Reinartz, K., Bevendorff, J., & Stein, B. (2018). A Stylometric Inquiry into Hyperpartisan and Fake News. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (Vol. 1, pp. 231-240). [2] https://pan.webis.de/semeval19/semeval19-web/index.html

Initial Plan (03/02/2020) [Zip Archive]

Final Report (15/05/2020) [Zip Archive]

Publication Form