HateXplain
Covers multiple aspects of the issue. Each post in the dataset is annotated from three different perspectives: the basic, commonly used 3-class classification (i.e., hate, offensive or normal), the target community (i.e., the community that has been the victim of hate speech/offensive speech in the post), and the rationales, i.e., the portions of the post on which their labelling decision (as hate, offensive or normal) is based.
Source: HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
Benchmarks
Abuse Detection/AUROCAbuse Detection/Macro F1Abuse Detection/AccuracyAbuse Detection/Macro-F1Classification/Accuracy (2 classes)Classification/F1 MacroHate Speech Detection/AUROCHate Speech Detection/Macro F1Hate Speech Detection/AccuracyHate Speech Detection/Macro-F1Text Classification/Accuracy (2 classes)Text Classification/F1 Macro