An Interdisciplinary Approach for the Automated Detection and Visualization of Media Bias in News Articles

TL;DR

This paper proposes an interdisciplinary approach combining NLP, deep learning, psychology, and linguistics to automatically detect and visualize media bias in news articles, aiming to increase reader awareness.

Contribution

It introduces a novel interdisciplinary methodology and demonstrates the potential of distant supervision with BERT models for bias detection.

Findings

Distant supervision improves bias detection performance.

Interdisciplinary methods enhance understanding of media bias.

Preliminary results show promising effectiveness of the approach.

Abstract

Media coverage has a substantial effect on the public perception of events. Nevertheless, media outlets are often biased. One way to bias news articles is by altering the word choice. The automatic identification of bias by word choice is challenging, primarily due to the lack of gold-standard data sets and high context dependencies. In this research project, I aim to devise data sets and methods to identify media bias. To achieve this, I plan to research methods using natural language processing and deep learning while employing models and using analysis concepts from psychology and linguistics. The first results indicate the effectiveness of an interdisciplinary research approach. My vision is to devise a system that helps news readers become aware of media coverage differences caused by bias. So far, my best performing BERT-based model is pre-trained on a larger corpus consisting of distant labels, indicating that distant supervision has the potential to become a solution for the difficult task of bias detection.