Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation
This addresses the issue of biased models for social media platforms and users, but it is incremental as it builds on existing methods with empirical validation.
The paper tackled the problem of dataset bias in hate speech detection by conducting a cross-dataset evaluation, finding that combining datasets leads to more robust models that outperform individual datasets even when controlling for data size.
The automatic detection of hate speech online is an active research area in NLP. Most of the studies to date are based on social media datasets that contribute to the creation of hate speech detection models trained on them. However, data creation processes contain their own biases, and models inherently learn from these dataset-specific biases. In this paper, we perform a large-scale cross-dataset comparison where we fine-tune language models on different hate speech detection datasets. This analysis shows how some datasets are more generalisable than others when used as training data. Crucially, our experiments show how combining hate speech detection datasets can contribute to the development of robust hate speech detection models. This robustness holds even when controlling by data size and compared with the best individual datasets.