Advanced BERT-CNN for Hate Speech Detection

Abstract

Hate Speech already been phenomenal expansion over the past decade. The paper proposed a new model that combines advanced CNN and Bidirectional Encoder Representations from Transformers (BERT) context embedding to predict hate speech in social media. This research trained contextual embedding on the datasets and used the learned information to identify objectionable language and hate speech in text. The paper evaluated supervised machine learning classifiers for bigoted and offensive content on Twitter using two datasets and found that advanced CNN context embeddings produced superior results. This research generated optimistic outcomes, which achieves 73% F1-score for Davidson dataset and 56% F1-score for TRAC-1 dataset

Topics & Concepts