This paper revisits the use of annotator demographics as interpretable meta-information for modeling such variation. We adapt a lightweight attention mechanism, Annotation-Wise Attention Network (AWAN), to condition predictions on demographic features, enabling per-annotator modeling. Experiments on the EXIST sexism dataset show that AWAN improves classification performance over standard baselines, especially in cases of high annotator disagreement.

This study explores the effect of annotators’ demographic features on labeling sexist content in social media datasets, specifically focusing on the EXIST dataset, which includes direct sexist messages, reports and descriptions of sexist experiences and stereotypes. We investigate how various demographic backgrounds influence annotation outcomes and examine methods to incorporate these features into BERT-based model training. Our experiments demonstrate that adding demographic information improves performance in detecting sexism and assessing intention of the author.