cardiffnlp/twitter-roberta-base-hate

This is a roBERTa-base model trained on ~58M tweets and finetuned for hate speech detection with the TweetEval benchmark . The model was trained on 58M tweets . It is a tool that can be used to detect hate speech in tweets . For example: "Not-hate 0.9168.1" and "Hate 0.0832.2" Hate 0.832.988.2) hate 0.1.0.3.2. For example, "Good night" is a text message that is preprocessed . The code is used to create a label mapping and label labels for each of the tasks . The data is,