@inproceedings{al-thubaity-etal-2022-aranpcc,
title = "{A}ra{NPCC}: The {A}rabic Newspaper {COVID}-19 Corpus",
author = "Al-Thubaity, Abdulmohsen and
Alkhereyf, Sakhar and
Bahanshal, Alia O.",
editor = "Al-Khalifa, Hend and
Elsayed, Tamer and
Mubarak, Hamdy and
Al-Thubaity, Abdulmohsen and
Magdy, Walid and
Darwish, Kareem",
booktitle = "Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.osact-1.4",
pages = "32--40",
abstract = "This paper introduces a corpus for Arabic newspapers during COVID-19: AraNPCC. The AraNPCC corpus covers 2019 until 2021 via automatically-collected data from 12 Arab countries. It comprises more than 2 billion words and 7.2 million texts alongside their metadata. AraNPCC can be used for several natural language processing tasks, such as updating available Arabic language models or corpus linguistics tasks, including language change over time. We utilized the corpus in two case studies. In the first case study, we investigate the correlation between the number of officially reported infected cases and the collective word frequency of {``}COVID{''} and {``}Corona.{''} The data shows a positive correlation that varies among Arab countries. For the second case study, we extract and compare the top 50 keywords in 2020 and 2021 to study the impact of the COVID-19 pandemic on two Arab countries, namely Algeria and Saudi Arabia. For 2020, the data shows that the two countries{'} newspapers strongly interacted with the pandemic, emphasizing its spread and dangerousness, and in 2021 the data suggests that the two countries coped with the pandemic.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-thubaity-etal-2022-aranpcc">
<titleInfo>
<title>AraNPCC: The Arabic Newspaper COVID-19 Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdulmohsen</namePart>
<namePart type="family">Al-Thubaity</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alia</namePart>
<namePart type="given">O</namePart>
<namePart type="family">Bahanshal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur’an QA and Fine-Grained Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulmohsen</namePart>
<namePart type="family">Al-Thubaity</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces a corpus for Arabic newspapers during COVID-19: AraNPCC. The AraNPCC corpus covers 2019 until 2021 via automatically-collected data from 12 Arab countries. It comprises more than 2 billion words and 7.2 million texts alongside their metadata. AraNPCC can be used for several natural language processing tasks, such as updating available Arabic language models or corpus linguistics tasks, including language change over time. We utilized the corpus in two case studies. In the first case study, we investigate the correlation between the number of officially reported infected cases and the collective word frequency of “COVID” and “Corona.” The data shows a positive correlation that varies among Arab countries. For the second case study, we extract and compare the top 50 keywords in 2020 and 2021 to study the impact of the COVID-19 pandemic on two Arab countries, namely Algeria and Saudi Arabia. For 2020, the data shows that the two countries’ newspapers strongly interacted with the pandemic, emphasizing its spread and dangerousness, and in 2021 the data suggests that the two countries coped with the pandemic.</abstract>
<identifier type="citekey">al-thubaity-etal-2022-aranpcc</identifier>
<location>
<url>https://aclanthology.org/2022.osact-1.4</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>32</start>
<end>40</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AraNPCC: The Arabic Newspaper COVID-19 Corpus
%A Al-Thubaity, Abdulmohsen
%A Alkhereyf, Sakhar
%A Bahanshal, Alia O.
%Y Al-Khalifa, Hend
%Y Elsayed, Tamer
%Y Mubarak, Hamdy
%Y Al-Thubaity, Abdulmohsen
%Y Magdy, Walid
%Y Darwish, Kareem
%S Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur’an QA and Fine-Grained Hate Speech Detection
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F al-thubaity-etal-2022-aranpcc
%X This paper introduces a corpus for Arabic newspapers during COVID-19: AraNPCC. The AraNPCC corpus covers 2019 until 2021 via automatically-collected data from 12 Arab countries. It comprises more than 2 billion words and 7.2 million texts alongside their metadata. AraNPCC can be used for several natural language processing tasks, such as updating available Arabic language models or corpus linguistics tasks, including language change over time. We utilized the corpus in two case studies. In the first case study, we investigate the correlation between the number of officially reported infected cases and the collective word frequency of “COVID” and “Corona.” The data shows a positive correlation that varies among Arab countries. For the second case study, we extract and compare the top 50 keywords in 2020 and 2021 to study the impact of the COVID-19 pandemic on two Arab countries, namely Algeria and Saudi Arabia. For 2020, the data shows that the two countries’ newspapers strongly interacted with the pandemic, emphasizing its spread and dangerousness, and in 2021 the data suggests that the two countries coped with the pandemic.
%U https://aclanthology.org/2022.osact-1.4
%P 32-40
Markdown (Informal)
[AraNPCC: The Arabic Newspaper COVID-19 Corpus](https://aclanthology.org/2022.osact-1.4) (Al-Thubaity et al., OSACT 2022)
ACL
- Abdulmohsen Al-Thubaity, Sakhar Alkhereyf, and Alia O. Bahanshal. 2022. AraNPCC: The Arabic Newspaper COVID-19 Corpus. In Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, pages 32–40, Marseille, France. European Language Resources Association.