This repository contains code for fine-tuning the BERT model on the Hate Speech Dataset obtained from a White Supremacy Forum. The goal is to perform short text classification using BERT.
Dataset The original Hate Speech Dataset from the White Supremacy Forum can be accessed hereLink. Please refer to the terms and conditions of the dataset provider before using it.
The processed version of the dataset is included in the repository under the data folder. You can find it here Link.
App. py file contains the streamlit code.