Efficient Hate Speech Detection: Evaluating 38 Models from Traditional Methods to Transformers
Mahmoud Abusaqer, Jamil M. Saquer, Hazim Shatnawi · 2025
The proliferation of hate speech on social media necessitates automated detection systems that balance accuracy with computational efficiency. This study evaluates 38 model configurations in detecting hate speech across datasets ranging from 6.5K to 451K samples. We analyze transformer architectures (e.g., BERT, RoBERTa, Distil-BERT), deep neural networks (e.g., CNN, LSTM, GRU, Hierarchical Attention Networks), and traditional machine learning methods (e.g., SVM, CatBoost, Random Forest).