@inproceedings{703acae27b124569b58fa4448ea1ee60,
title = "ArCOV-19: The First Arabic COVID-19 Twitter Dataset with Propagation Networks",
abstract = "In this paper, we present ArCOV-19, an Arabic COVID-19 Twitter dataset that spans one year, covering the period from 27th of January 2020 till 31st of January 2021. ArCOV-19 is the first publicly-available Arabic Twitter dataset covering COVID-19 pandemic that includes about 2.7M tweets alongside the propagation networks of the most-popular subset of them (i.e., most-retweeted and-liked). The propagation networks include both retweets and conversational threads (i.e., threads of replies). ArCOV-19 is designed to enable research under several domains including natural language processing, information retrieval, and social computing. Preliminary analysis shows that ArCOV-19 captures rising discussions associated with the first reported cases of the disease as they appeared in the Arab world. In addition to the source tweets and propagation networks, we also release the search queries and languageindependent crawler used to collect the tweets to encourage the curation of similar datasets.",
author = "Fatima Haouari and Maram Hasanain and Reem Suwaileh and Tamer Elsayed",
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 = "82--91",
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",
}