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.

The propagation of offensive content through social media channels has garnered attention of the research community. Multiple works have proposed various semantically related yet subtle distinct categories of offensive speech. In this work, we explore meta-earning approaches to leverage the diversity of offensive speech corpora to enhance their reliable and efficient detection. We propose a joint embedding architecture that incorporates the input's label and definition for classification via Prototypical Network. Our model achieves at least 75% of the maximal F1-score while using less than 10% of the available training data across 4 datasets. Our experimental findings also provide a case study of training strategies valuable to combat resource scarcity.

The spread of information through social media platforms can create environments possibly hostile to vulnerable communities and silence certain groups in society. To mitigate such instances, several models have been developed to detect hate and offensive speech. Since detecting hate and offensive speech in social media platforms could incorrectly exclude individuals from social media platforms, which can reduce trust, there is a need to create explainable and interpretable models. Thus, we build an explainable and interpretable high performance model based on the XGBoost algorithm, trained on Twitter data. For unbalanced Twitter data, XGboost outperformed the LSTM, AutoGluon, and ULMFiT models on hate speech detection with an F1 score of 0.75 compared to 0.38 and 0.37, and 0.38 respectively. When we down-sampled the data to three separate classes of approximately 5000 tweets, XGBoost performed better than LSTM, AutoGluon, and ULMFiT; with F1 scores for hate speech detection of 0.79 vs 0.69, 0.77, and 0.66 respectively. XGBoost also performed better than LSTM, AutoGluon, and ULMFiT in the down-sampled version for offensive speech detection with F1 score of 0.83 vs 0.88, 0.82, and 0.79 respectively. We use Shapley Additive Explanations (SHAP) on our XGBoost models' outputs to makes it explainable and interpretable compared to LSTM, AutoGluon and ULMFiT that are black-box models.

For all the advances being made in the field, artificial intelligence still struggles when it comes to identifying hate speech. When he testified before Congress in April, Facebook CEO Mark Zuckerberg said it was "one of the hardest" problems. But, he went on, he was optimistic that "over a five- to 10-year period, we will have AI tools that can get into some of the linguistic nuances of different types of content to be more accurate in flagging things for our systems." For that to happen, however, humans will need first to define for ourselves what hate speech means--and that can be hard because it's constantly evolving and often dependent on context. "Hate speech can be tricky to detect since it is context and domain dependent. Trolls try to evade or even poison such [machine learning] classifiers," says Aylin Caliskan, a computer science researcher at George Washington University who studies how to fool artificial intelligence.