Towards Weakly-Supervised Hate Speech Classification Across Datasets
This addresses a critical issue for researchers and practitioners in hate speech detection by improving cross-dataset comparability and generalization, though it is incremental as it builds on existing weakly-supervised methods.
The paper tackles the problem of poor generalization in hate speech classification across datasets with different annotation schemata by applying extremely weak supervision that relies only on class names, demonstrating its effectiveness in various settings and analyzing the sources of poor generalizability.
As pointed out by several scholars, current research on hate speech (HS) recognition is characterized by unsystematic data creation strategies and diverging annotation schemata. Subsequently, supervised-learning models tend to generalize poorly to datasets they were not trained on, and the performance of the models trained on datasets labeled using different HS taxonomies cannot be compared. To ease this problem, we propose applying extremely weak supervision that only relies on the class name rather than on class samples from the annotated data. We demonstrate the effectiveness of a state-of-the-art weakly-supervised text classification model in various in-dataset and cross-dataset settings. Furthermore, we conduct an in-depth quantitative and qualitative analysis of the source of poor generalizability of HS classification models.