Home > Research > Publications & Outputs > COVID-19 and Arabic Twitter

Electronic data

Links

View graph of relations

COVID-19 and Arabic Twitter: How can Arab World Governments and Public Health Organizations Learn from Social Media?

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

COVID-19 and Arabic Twitter : How can Arab World Governments and Public Health Organizations Learn from Social Media? / Alsudias, Lama; Rayson, Paul.

NLP COVID-19 Workshop : an emergency workshop at ACL 2020. Association for Computational Linguistics, 2020.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Alsudias, L & Rayson, P 2020, COVID-19 and Arabic Twitter: How can Arab World Governments and Public Health Organizations Learn from Social Media? in NLP COVID-19 Workshop : an emergency workshop at ACL 2020. Association for Computational Linguistics, NLP COVID-19 Workshop , 9/07/20. <https://www.aclweb.org/anthology/2020.nlpcovid19-acl.16/>

APA

Vancouver

Alsudias L, Rayson P. COVID-19 and Arabic Twitter: How can Arab World Governments and Public Health Organizations Learn from Social Media? In NLP COVID-19 Workshop : an emergency workshop at ACL 2020. Association for Computational Linguistics. 2020

Author

Alsudias, Lama ; Rayson, Paul. / COVID-19 and Arabic Twitter : How can Arab World Governments and Public Health Organizations Learn from Social Media?. NLP COVID-19 Workshop : an emergency workshop at ACL 2020. Association for Computational Linguistics, 2020.

Bibtex

@inproceedings{65305093fb2942ee998350f3d94a85e2,
title = "COVID-19 and Arabic Twitter: How can Arab World Governments and Public Health Organizations Learn from Social Media?",
abstract = "In March 2020, the World Health Organization announced the COVID-19 outbreak as a pandemic. Most previous social media related research has been on English tweets and COVID-19. In this study, we collect approximately 1 million Arabic tweets from the Twitter streaming API related to COVID-19. Focussing on outcomes that we believe will be useful for Public Health Organizations, we analyse them in three different ways: identifying the topics discussed during the period, detecting rumours, and predicting the source of the tweets. We use the k-means algorithm for the first goal with k=5. The topics discussed can be grouped as follows: COVID-19 statistics, prayers for God, COVID-19 locations, advise and education for prevention, and advertising. We sample 2000 tweets and label them manually for false information, correct information, and unrelated. Then, we apply three different machine learning algorithms, Logistic Regression, Support Vector Classification, and Na{\"i}ve Bayes with two sets of features, word frequency approach and word embeddings. We find that Machine Learning classifiers are able to correctly identify the rumour related tweets with 84% accuracy. We also try to predict the source of the rumour related tweets depending on our previous model which is about classifying tweets into five categories: academic, media, government, health professional, and public. Around (60%) of the rumour related tweets are classified as written by health professionals and academics.",
author = "Lama Alsudias and Paul Rayson",
year = "2020",
month = oct,
day = "27",
language = "English",
booktitle = "NLP COVID-19 Workshop",
publisher = "Association for Computational Linguistics",
note = "NLP COVID-19 Workshop : an emergency workshop at ACL 2020 ; Conference date: 09-07-2020",
url = "https://www.nlpcovid19workshop.org/",

}

RIS

TY - GEN

T1 - COVID-19 and Arabic Twitter

T2 - NLP COVID-19 Workshop

AU - Alsudias, Lama

AU - Rayson, Paul

PY - 2020/10/27

Y1 - 2020/10/27

N2 - In March 2020, the World Health Organization announced the COVID-19 outbreak as a pandemic. Most previous social media related research has been on English tweets and COVID-19. In this study, we collect approximately 1 million Arabic tweets from the Twitter streaming API related to COVID-19. Focussing on outcomes that we believe will be useful for Public Health Organizations, we analyse them in three different ways: identifying the topics discussed during the period, detecting rumours, and predicting the source of the tweets. We use the k-means algorithm for the first goal with k=5. The topics discussed can be grouped as follows: COVID-19 statistics, prayers for God, COVID-19 locations, advise and education for prevention, and advertising. We sample 2000 tweets and label them manually for false information, correct information, and unrelated. Then, we apply three different machine learning algorithms, Logistic Regression, Support Vector Classification, and Naïve Bayes with two sets of features, word frequency approach and word embeddings. We find that Machine Learning classifiers are able to correctly identify the rumour related tweets with 84% accuracy. We also try to predict the source of the rumour related tweets depending on our previous model which is about classifying tweets into five categories: academic, media, government, health professional, and public. Around (60%) of the rumour related tweets are classified as written by health professionals and academics.

AB - In March 2020, the World Health Organization announced the COVID-19 outbreak as a pandemic. Most previous social media related research has been on English tweets and COVID-19. In this study, we collect approximately 1 million Arabic tweets from the Twitter streaming API related to COVID-19. Focussing on outcomes that we believe will be useful for Public Health Organizations, we analyse them in three different ways: identifying the topics discussed during the period, detecting rumours, and predicting the source of the tweets. We use the k-means algorithm for the first goal with k=5. The topics discussed can be grouped as follows: COVID-19 statistics, prayers for God, COVID-19 locations, advise and education for prevention, and advertising. We sample 2000 tweets and label them manually for false information, correct information, and unrelated. Then, we apply three different machine learning algorithms, Logistic Regression, Support Vector Classification, and Naïve Bayes with two sets of features, word frequency approach and word embeddings. We find that Machine Learning classifiers are able to correctly identify the rumour related tweets with 84% accuracy. We also try to predict the source of the rumour related tweets depending on our previous model which is about classifying tweets into five categories: academic, media, government, health professional, and public. Around (60%) of the rumour related tweets are classified as written by health professionals and academics.

M3 - Conference contribution/Paper

BT - NLP COVID-19 Workshop

PB - Association for Computational Linguistics

Y2 - 9 July 2020

ER -