Multi-task Learning with Active Learning for Arabic Offensive Speech Detection

TL;DR

This paper presents a novel framework combining multi-task learning and active learning to improve Arabic offensive speech detection, achieving state-of-the-art results with fewer labeled samples.

Contribution

It introduces an integrated MTL and active learning approach with dynamic task weighting and emoji handling for better Arabic offensive speech detection.

Findings

Achieved macro F1-score of 85.42% on OSACT2022 dataset

Outperformed existing methods with fewer labeled samples

Demonstrated effectiveness of combined MTL and active learning strategies

Abstract

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 paper 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 the 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 on 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 for efficient and accurate offensive language detection in resource-constrained settings.