Romanian Journal of Information Technology and Automatic Control
Areej ALSHUTAYRI1, Amal ALGHAMDI1, Nouran NASSIBI1, Nahla ALJOJO2, Eman ALDHAHRI1, Omar ABOULOLA2
1 Department of Computer Science and Artificial Intelligence, College of Computer Science and Engineering
University of Jeddah, Jeddah, Saudi Arabia
2 Department of Information Systems and Technology, College of Computer Science and Engineering
University of Jeddah, Jeddah, Saudi Arabia
aoalshutayri@uj.edu.sa, aalghamdi3523.stu@uj.edu.sa, nnassibi.stu@uj.edu.sa, eaal-dhahery@uj.edu.sa
nmaljojo@uj.edu.sa, oaboulola@uj.edu.sa
Abstract: The purpose of this article was to highlight the sentiment analysis for specific Arabic tweets related to the COVID-19 Worldwide Epidemic. The technique proposed in this paper focused on using the machine learning algorithm with the purpose of applying sentiment analysis on a dataset which contained 4,575 Arabic tweets on the COVID-19 pandemic while also employing the Logistic Regression and Naive Bayes algorithms as classifiers for comparing the achieved results between them. This study showed the suitability and efficiency of a system using machine learning models for the analysis of Arabic tweets. The experimental outcomes revealed that the highest accuracy was reached by employing the Logistic Regression algorithm”, namely, 97%”. Twitter is one of the most widely used gateways of social media for the people who want to express their opinions and emotions. This study contributes to highlighting the task of sentiment analysis for the Arabic tweets about the COVID-19 pandemic by predicting the people’s awareness about the Coronavirus in the Arab World.
Keywords: COVID-19, Arabic tweets, Sentiment Analysis, Machine Learning, Twitter.
CITE THIS PAPER AS:
Areej ALSHUTAYRI, Amal ALGHAMDI, Nouran NASSIBI, Nahla ALJOJO, Eman ALDHAHRI, Omar ABOULOLA, Sentiment analysis for Arabic tweet about the COVID-19 Worldwide Epidemic, Romanian Journal of Information Technology and Automatic Control, ISSN 1220-1758, vol. 32(2), pp. 127-136, 2022. https://doi.org/10.33436/v32i2y202210