TweetBLM: A Hate Speech Dataset and Analysis of Black Lives Matter-related Microblogs on Twitter:

In the past few years, there has been a significant rise in toxic and hateful content on various social media platforms. Recently Black Lives Matter movement came into the picture again causing an avalanche of user-generated response on the internet. In this paper, we have proposed a Black Lives Matter related tweet hate speech dataset- TweetBLM. Our dataset is consists of 9165 manually annotated tweets that target the Black Lives Matter movement. The tweets were annotated into two classes, i.e, ”HATE” and ”NON-HATE” on the basis of their content related to racism erupted from the movement. In this work, we also generated useful insights on our dataset and performed a systematic analysis of various state-of-the-art models such as LSTM, Bi-LSTM, Fasttext, BERTbase and BERTlarge for the classification task on our dataset. Through our work, we aim at contributing to the substantial efforts of the research community for identification and mitigation of hate speech on the internet.