Multi-task Learning with Active Learning for Arabic Offensive Speech Detection
ACM Transactions on Asian and Low-Resource Language Information Processing · 30.11.2026 · 25 (11) · 1-20
DOI: 10.1145/3848627 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Asian and Low-Resource Language Information Processing, online erschienen am 05.11.2026. Verfasst von Aisha Alansari und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The rapid growth of social media has amplified the spread of offensive, violent, and vulgar speech, which poses serious societal and cybersecurity concerns. Detecting such content in Arabic text is particularly complex due to limited labeled data, dialectal variations, and the language’s inherent complexity. This article proposes a novel framework that integrates multi-task learning (MTL) with active learning to enhance offensive speech detection in Arabic social media text. By jointly training on two auxiliary tasks, violent and vulgar speech, the model leverages shared representations to improve the detection accuracy of offensive speech. Our approach dynamically adjusts task weights during training to balance the contribution of each task and optimize performance. To address the scarcity of labeled data, we employ an active learning strategy through several uncertainty sampling techniques to iteratively select the most informative samples for model training. We also introduce weighted emoji handling to better capture semantic cues. Experimental results using the OSACT2022 dataset show that the proposed framework achieves a state-of-the-art macro F1-score of 85.42%, outperforming existing methods while using significantly fewer fine-tuning samples. The findings of this study highlight the potential of integrating MTL with active learning to efficiently and accurately detect offensive language in resource-constrained settings.
Zitieren
APA
Alansari, A., & Luqman, H. (2026). Multi-task Learning with Active Learning for Arabic Offensive Speech Detection. ACM Transactions on Asian and Low-Resource Language Information Processing, 25(11), 1-20. https://doi.org/10.1145/3848627
Vancouver
Alansari A, Luqman H. Multi-task Learning with Active Learning for Arabic Offensive Speech Detection. ACM Transactions on Asian and Low-Resource Language Information Processing. 2026;25(11):1-20. doi:10.1145/3848627
BibTeX
@article{Alansari2026,
author = {Alansari, Aisha and Luqman, Hamzah},
title = {Multi-task Learning with Active Learning for Arabic Offensive Speech Detection},
journal = {ACM Transactions on Asian and Low-Resource Language Information Processing},
year = {2026},
volume = {25},
number = {11},
pages = {1--20},
doi = {10.1145/3848627}
}
EUVIMED