@inproceedings{haouari-etal-2021-arcov,
title = "{A}r{COV}-19: The First {A}rabic {COVID}-19 {T}witter Dataset with Propagation Networks",
author = "Haouari, Fatima and
Hasanain, Maram and
Suwaileh, Reem and
Elsayed, Tamer",
booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
month = apr,
year = "2021",
address = "Kyiv, Ukraine (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wanlp-1.9",
pages = "82--91",
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 retweetsand 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 the propagation networks, we also release the search queries and the language-independent crawler used to collect the tweets to encourage the curation of similar datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="haouari-etal-2021-arcov">
<titleInfo>
<title>ArCOV-19: The First Arabic COVID-19 Twitter Dataset with Propagation Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fatima</namePart>
<namePart type="family">Haouari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maram</namePart>
<namePart type="family">Hasanain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reem</namePart>
<namePart type="family">Suwaileh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-apr</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv, Ukraine (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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 retweetsand 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 the propagation networks, we also release the search queries and the language-independent crawler used to collect the tweets to encourage the curation of similar datasets.</abstract>
<identifier type="citekey">haouari-etal-2021-arcov</identifier>
<location>
<url>https://aclanthology.org/2021.wanlp-1.9</url>
</location>
<part>
<date>2021-apr</date>
<extent unit="page">
<start>82</start>
<end>91</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArCOV-19: The First Arabic COVID-19 Twitter Dataset with Propagation Networks
%A Haouari, Fatima
%A Hasanain, Maram
%A Suwaileh, Reem
%A Elsayed, Tamer
%S Proceedings of the Sixth Arabic Natural Language Processing Workshop
%D 2021
%8 apr
%I Association for Computational Linguistics
%C Kyiv, Ukraine (Virtual)
%F haouari-etal-2021-arcov
%X 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 retweetsand 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 the propagation networks, we also release the search queries and the language-independent crawler used to collect the tweets to encourage the curation of similar datasets.
%U https://aclanthology.org/2021.wanlp-1.9
%P 82-91
Markdown (Informal)
[ArCOV-19: The First Arabic COVID-19 Twitter Dataset with Propagation Networks](https://aclanthology.org/2021.wanlp-1.9) (Haouari et al., WANLP 2021)
ACL