Spam Detection on Arabic Twitter

Hamdy Mubarak, Ahmed Abdelali, Sabit Hassan, Kareem Darwish

Abstract: Twitter has become a popular social media platform in the Arab region. Some users exploit this popularity by posting unwanted advertisements for their own interest. In this paper, we present a large manually annotated dataset of advertisement (Spam) tweets in Arabic. We analyze the characteristics of these tweets that distinguish them from other tweets and identify their targets and topics. In addition, we analyze the characteristics of Spam accounts. We utilize Support Vector Machines (SVMs) and contextual embedding based models to identify these Spam tweets with macro averaged F1 score above 98%.