HausaNLP at SemEval-2025 Task 11: Hausa Text Emotion Detection
Sani, Sani Abdullahi, Abubakar, Salim, Lawan, Falalu Ibrahim, Abubakar, Abdulhamid, Bala, Maryam
–arXiv.org Artificial Intelligence
This paper presents our approach to multi-label emotion detection in Hausa, a low-resource African language, for SemEval Track A. We fine-tuned AfriBERTa, a transformer-based model pre-trained on African languages, to classify Hausa text into six emotions: anger, disgust, fear, joy, sadness, and surprise. Our methodology involved data preprocessing, tokenization, and model fine-tuning using the Hugging Face Trainer API. The system achieved a validation accuracy of 74.00%, with an F1-score of 73.50%, demonstrating the effectiveness of transformer-based models for emotion detection in low-resource languages.
arXiv.org Artificial Intelligence
Jun-24-2025
- Country:
- Africa
- Central Africa (0.04)
- Niger (0.04)
- Nigeria > Kaduna State
- Kaduna (0.04)
- Asia > Singapore (0.04)
- Europe
- Austria > Vienna (0.14)
- France > Provence-Alpes-Côte d'Azur
- Bouches-du-Rhône > Marseille (0.04)
- Switzerland (0.04)
- North America
- Canada > Ontario
- Toronto (0.04)
- Dominican Republic (0.04)
- United States > Texas
- Dallas County > Dallas (0.04)
- Canada > Ontario
- Africa
- Genre:
- Research Report (0.82)
- Technology: