@inproceedings{f28e45c140fd4c2cb51736518bbf2f05,
title = "Arabic Offensive Language on Twitter: Analysis and Experiments",
abstract = "Detecting offensive language on Twitter has many applications ranging from detecting/predicting bullying to measuring polarization. In this paper, we focus on building a large Arabic offensive tweet dataset. We introduce a method for building a dataset that is not biased by topic, dialect, or target. We produce the largest Arabic dataset to date with special tags for vulgarity and hate speech. We thoroughly analyze the dataset to determine which topics, dialects, and gender are most associated with offensive tweets and how Arabic speakers use offensive language. Lastly, we conduct many experiments to produce strong results (F1 = 83.2) on the dataset using SOTA techniques.",
author = "Hamdy Mubarak and Ammar Rashed and Kareem Darwish and Younes Samih and Ahmed Abdelali",
note = "Publisher Copyright: {\textcopyright} WANLP 2021 - 6th Arabic Natural Language Processing Workshop; 6th Arabic Natural Language Processing Workshop, WANLP 2021 ; Conference date: 19-04-2021",
year = "2021",
language = "English",
series = "WANLP 2021 - 6th Arabic Natural Language Processing Workshop, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "126--135",
editor = "Nizar Habash and Houda Bouamor and Hazem Hajj and Walid Magdy and Wajdi Zaghouani and Fethi Bougares and Nadi Tomeh and Farha, {Ibrahim Abu} and Samia Touileb",
booktitle = "WANLP 2021 - 6th Arabic Natural Language Processing Workshop, Proceedings of the Workshop",
address = "United States",
}