@inproceedings{fe17bf4dd39c424a9292b8caff61a304,
title = "Spam Detection on Arabic Twitter",
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%.",
keywords = "Advertisement detection, Arabic social media, Social media analysis, Spam filtering",
author = "Hamdy Mubarak and Ahmed Abdelali and Sabit Hassan and Kareem Darwish",
note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.; 12th International Conference on Social Informatics, SocInfo 2020 ; Conference date: 06-10-2020 Through 09-10-2020",
year = "2020",
doi = "10.1007/978-3-030-60975-7_18",
language = "English",
isbn = "9783030609740",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "237--251",
editor = "Samin Aref and Kalina Bontcheva and Marco Braghieri and Frank Dignum and Fosca Giannotti and Francesco Grisolia and Dino Pedreschi",
booktitle = "Social Informatics - 12th International Conference, SocInfo 2020, Proceedings",
address = "Germany",
}