We present improved models for the granular detection and sub-classification news media bias in English news articles. We compare the performance of zero-shot versus fine-tuned large pre-trained neural transformer language models, explore how the level of detail of the classes affects performance on a novel taxonomy of 27 news bias-types, and demonstrate how using synthetically generated example data can be used to improve quality
@article{arxiv.2412.11835,
title = {Improved Models for Media Bias Detection and Subcategorization},
author = {Tim Menzner and Jochen L. Leidner},
journal= {arXiv preprint arXiv:2412.11835},
year = {2026}
}