Hate speech detection in social media messages (Tweets) using BERT model

Abstract

Hate speech is harmful online content that directly attacks or promotes hatred against members of groups or individuals based on actual or perceived aspects of identity, such as racism, religion, or sexual orientation. This can affect social life on social media platforms as hateful content shared through social media can harm both individuals and communities. As the prevalence of hate speech increases online, the demand for automated detection as an NLP task is increasing. In this project, the proposed method is using transformer based model i.e. BERT to detect hate speech in social media texts, mainly in tweets. This model works well in various languages such as Bengali, English, German, Italian. The success rate of using this model for hate speech detection is high enough to prove that BERT model is appropriate model for hate speech detection (Accuracy in Bengali dataset is 89%, in English: 91%, in German dataset 91% and in Italian dataset it is 77% ).