🤖 AI Summary
This study addresses the challenge of hate speech detection in Algerian Arabic Darija on social media, where linguistic complexity arises from the mixing of Arabic, French, and Arabizi. To tackle this issue, the authors propose a hybrid GRU-based architecture that integrates multi-source embeddings—specifically DZ FastText, DZ AraVec, and DziriBERT—and enhances sequence modeling through a self-attention mechanism to improve semantic representation. Evaluated on a Darija dataset under low-resource conditions, the model achieves 93.2% accuracy, 92.1% F1-score, and 97.0% ROC-AUC, significantly outperforming baseline approaches including traditional machine learning models, RNNs, and Transformers. These results demonstrate the effectiveness of combining multiple dialectal embeddings with attention mechanisms for hate speech detection in resource-constrained, linguistically heterogeneous settings.
📝 Abstract
The widespread adoption of social media platforms has transformed online communication by enabling users to exchange information and opinions instantly. However, these platforms have also facilitated the dissemination of abusive and hateful content, posing major social, psychological, and ethical challenges. Hate speech can incite discrimination, harassment, and violence against individuals or communities based on attributes such as ethnicity, religion, gender, nationality, or political affiliation. Consequently, automatic hate speech detection has become a major research topic in natural language processing (NLP) and an essential component of content moderation systems.
This paper investigates automatic hate speech detection in the Algerian Arabic dialect (Darija) on social media. This task remains challenging because of the dialect's linguistic diversity, characterized by the coexistence of Arabic, French, and Arabizi (Arabic written using the Latin alphabet). We compare four categories of text classification approaches: (1) traditional machine learning models using TF-IDF features, (2) deep learning models based on recurrent neural networks, (3) Transformer-based language models, including DziriBERT and multilingual BERT, and (4) a novel hybrid architecture, FAD-SA-GRU, which combines semantic representations from DZ FastText, DZ AraVec, and DziriBERT through multi-embedding fusion, followed by a self-attention-enhanced GRU encoder.
Experiments on an annotated dataset of Algerian Darija social media comments for binary hate speech classification show that FAD-SA-GRU outperforms all baselines, achieving 93.2% accuracy, 93.4% precision, 91.0% recall, 92.1% F1-score, and 97.0% ROC-AUC. Results demonstrate the effectiveness of combining complementary embedding representations with attention-based sequence modeling for robust hate speech detection in low-resource dialectal Arabic.