BiasScanner: Automatic News Bias Classification for Strengthening Democracy

Abstract

The increasing consumption of news online in the 21st century coincided with increased publication of disinformation, biased reporting, hate speech and other unwanted Web content.

We describe BiasScanner, an application that aims to strengthen democracy by supporting news consumers with scrutinizing news articles they are reading online. BiasScanner contains a server-side pre-trained large language model to identify biased sentences of news articles and a front-end Web browser plug-in. BiasScanner can identify and classify more than two dozen types of media bias at the sentence level, making it the most fine-grained model and only automatic application deployed as a browser plug-in. One special feature is the high-quality, LLM-generated explanations of the model’s decisions.

While prior research has addressed news bias detection, we are not aware of any automatic work that resulted in a deployed browser plug-in (c.f. also biasscanner.org for a Web demo).

mehr

Mehr zum Titel

Titel	BiasScanner: Automatic News Bias Classification for Strengthening Democracy
Medien	Advances in Information Retrieval: Proceedings of the 47th European Conference on Information Retrieval (ECIR 2025), Lucca, Italy, April 6–10, 2025
Verlag	Springer Nature
Herausgeber	Hauff, Claudia and Macdonald, Craig and Jannach, Dietmar and Kazai, Gabriella and Nardini, Franco Maria and Pinelli, Fabio and Silvestri, Fabrizio and Tonellotto, Nicola
Band	IV
ISBN	978-3-031-88720-8
Verfasser	Tim Menzner, Prof. Dr. Jochen L. Leidner
Seiten	105-110
Veröffentlichungsdatum	08.04.2025
Projekttitel	BiasScanner
Zitation	Menzner, Tim; Leidner, Jochen L. (2025): BiasScanner: Automatic News Bias Classification for Strengthening Democracy. Advances in Information Retrieval: Proceedings of the 47th European Conference on Information Retrieval (ECIR 2025), Lucca, Italy, April 6–10, 2025 IV, 105-110. DOI: 10.1007/978-3-031-88720-8_18