An Overview of Artificial Intelligence in the Detection of Suspicious Arabic Text on Social Media Platforms

This study examines the challenges of detecting and classifying offensive language in Arabic, with a focus on natural language processing (NLP) methods. Arabic's distinctive linguistic characteristics, such as its extensive morphology, present substantial obstacles to accurately classifying offensive content. This paper evaluates the approaches currently in use in this field and conducts a critical analysis of publicly accessible datasets frequently used to detect offensive language in Arabic. In addition to highlighting areas for further study and growth in the detection of Arabic offensive language, the aim is to offer insights into the state-of-the-art methodologies being used. In the analysis of public datasets, this paper evaluates their suitability for offensive language detection tasks in Arabic, considering factors such as dataset size, annotation quality, and representation of diverse offensive language categories. Furthermore, this paper investigates the existing methods utilized for detecting and classifying offensive language in Arabic, examining a range of NLP approaches used in the context of detecting Arabic offensive language. This includes machine learning algorithms, deep learning architectures, and linguistic aspects, all tailored to address the specific challenges associated with offensive language detection in the Arabic vernacular. Our investigation emphasizes the need for customized algorithms that take into account Arabic's unique linguistic characteristics. Future research should focus on developing advanced models that incorporate domain-specific knowledge, handle dialectal variations, and effectively capture the intricacies of Arabic morphology.