Using Transfer-based Language Models to Detect Hateful and Offensive Language Online (Proceedings of the Fourth Workshop on Online Abuse and Harms)

The dataset is curated from Twitter, annotated manually. Our dataset consists of over 25000 distinct tweets labeled into four major classes i.e hate, offensive, profane, and not. We present the

In recent years, successful hate speech detection models have been developed, such as using CNN, LSTM, but they lack a sufficient amount of discriminative power. In order to tackle the