asbichi362/AbjadNLP2026_HACS-TL

Cross-Script Transfer Learning for Hausa Ajami Hate Speech Detection Using Transformer-Based Architecture, click below link to view complete implementation # AbjadNLP2026_HACS-TL Cross-Script Transfer Learning for Hausa Ajami Hate Speech Detection Using Transformer-Based Architecture. **Abstract** Hausa is one of the most widely spoken languages in West Africa and uses two scripts: the Boko Latin and the Ajami Arabic-derived script. Although Ajami is culturally important, it is still very underrepresented in natural language processing. In this paper, HACS-TL, a novel transformer-based architecture for detecting hate speech in Hausa Ajami, is proposed. Our model uses a linguistically motivated Latin-to-Hausa Ajami converter, cross-script attention, and dialectspecific pooling. After conducting extensive 2-fold cross-validation on 2,000 samples, we found that HACS-TL outperformed baseline models (mBERT (73.70%), XLMRoBERTa (67.20%), and AraBERT (56.96%)) with a macro F1 score of 75.33%. Detailed error analyses and orthographic stress tests demonstrate the robustness of this approach. The proposed Hausa Ajami conversion system achieved 63.57% character-level similarity with 51% correct conversions, thereby establishing a baseline for the computational processing of Ajami Hausa. **Click this googble drive to view complete implementation contain dataset, codes, and experimental results.** [Click link here] (drive.google.com)