Search

Different social media platforms have become increasingly popular in the Arab world in recent years. The increasing use of social media, however, has also led to the emergence of a new challenge in the form of abusive content, including hate speech, offensive language, and abusive language. Existing research work focuses on automatic abusive content detection as a binary classification problem. In addition, the existing research work on the automatic detection task surrounding abusive Arabic content fails to tackle the dialect-specific phenomenon. Consequently, this has led to two important issues in the automatic abusive Arabic content detection task. In this study, we used a multi-aspect annotation schema to tackle the automatic abusive content detection problem in Arabic countries, based on the multi-class classification task and the dialectal Arabic (DA)-specific phenomenon. More precisely, the multi-aspect annotation schema includes five attributes: directness, hostility, target, group, and annotator. We specifically developed a framework to automatically detecting abusive content on Twitter using natural language processing (NLP) techniques. The developed framework used different models of machine learning (ML), deep learning (DL), and pretrained Arabic language models (LMs) using the multi-aspect annotation dataset. In addition, to investigate the impact of the other approaches, such as multi-task learning (MTL), we developed four MTL models built on top of a pretrained DA language model (called MARBERT) and trained on the multi-aspect annotation dataset. Our MTL models and pretrained Arabic LMs enhanced the performance compared to the existing DL model mentioned in the literature. [ABSTRACT FROM AUTHOR]

The proliferation of social media platforms resulted in a remarkable increase in user-generated content. These platforms have empowered users to create, share and exchange content for interacting and communicating with each other. However, these have also opened new avenues to cyber-bullies and haters who can spread their negativity to a larger audience, often anonymously. Due to the pervasiveness and severity of this behavior, many automated approaches that employ natural language processing (NLP), machine learning and deep learning techniques have been proposed in the past. This survey offers an extensive overview of the state-of-the-art approaches proposed by research community to identify offensive content. Based on our comprehensive literature survey, a categorization of different approaches and features employed by the researchers in the detection process are presented. This survey also incorporates the major challenges that require considerable research efforts in this domain. Finally, future research directions with an aim of developing robust abusive content detection system for social media are also discussed. [ABSTRACT FROM AUTHOR]