A Domain-adaptive Pre-training Approach for Language Bias Detection in News
This work addresses media bias detection, a domain-specific problem for news analysis, with incremental improvements over prior methods.
The paper tackled the problem of detecting biased word choices in news, a challenging task due to linguistic complexity and lack of gold-standard data, and achieved a state-of-the-art F1 score of 0.814 with their domain-adapted transformer model.
Media bias is a multi-faceted construct influencing individual behavior and collective decision-making. Slanted news reporting is the result of one-sided and polarized writing which can occur in various forms. In this work, we focus on an important form of media bias, i.e. bias by word choice. Detecting biased word choices is a challenging task due to its linguistic complexity and the lack of representative gold-standard corpora. We present DA-RoBERTa, a new state-of-the-art transformer-based model adapted to the media bias domain which identifies sentence-level bias with an F1 score of 0.814. In addition, we also train, DA-BERT and DA-BART, two more transformer models adapted to the bias domain. Our proposed domain-adapted models outperform prior bias detection approaches on the same data.