“Through this work, we propose some solutions for the problem of automatic detection of hate messages. We perform hate speech classification using embedding representations of words and Deep Neural Networks (DNN). We compare fastText and BERT (Bidirectional Encoder Representations from Transformers) embedding representations of words. Furthermore, we perform classification using two approaches: (a) using word embeddings as input to Support Vector Machines (SVM) and DNN-based classifiers; (b) fine-tuning of a BERT model for classification using a taskspecific corpus. Among the DNN-based classifiers, we compare Convolutional Neural Networks (CNN), Bi-Directional Long Short Term Memory (Bi-LSTM) and Convolutional Recurrent Neural Network (CRNN). The classification was performed on a Twitter dataset using three classes: hate, offensive and neither classes. Compared to the feature-based approaches, the BERT fine-tuning approach obtained a relative improvement of 16% in terms of macro-average F1-measure and 5.3% in terms of weighted F1-measure.”
https://hal.archives-ouvertes.fr/hal-03101938/document