BiasScanner: Automatic Detection and Classification of News Bias to Strengthen Democracy

TL;DR

BiasScanner is a novel browser plugin that uses a large language model to detect, classify, and explain over two dozen types of media bias at the sentence level, aiming to promote democratic discourse.

Contribution

It introduces the first deployed, fine-grained bias detection system with explainability, integrated into a lightweight browser plugin for real-time news analysis.

Findings

Detects and classifies 24+ bias types at sentence level

Provides explanations and summaries for bias classifications

Deployed as a privacy-respecting browser plugin

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. At the time of writing, 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 deployed application (automatic system in use) of its kind. It was implemented in a light-weight and privacy-respecting manner, and in addition to highlighting likely biased sentence it also provides explanations for each classification decision as well as a summary analysis for each news article. While prior research has addressed news bias detection, we are not aware of any work that resulted in a deployed browser plug-in (c.f. also biasscanner.org for a Web demo).