DETECTING CORONAVIRUS DISEASE OF ARABIC TWEETS USING SENTIMENT ANALYSIS

Authors

  • A. R. Alobaidi Department of Computer Techniques Engineering, Faculty of Information Technology, Imam Ja’afar Al-Sadiq University, Baghdad, Iraq
  • Z. N. Nuimi Department of Electrical Engineering, Faculty of Engineering, University of Mayasan, Mayasan, Iraq

Abstract


In order to detect COVID-19 from Arabic tweets, we used five machine learning algorithms which are Support Vector Machine, Decision Tree, Multinomial Naive Bayes, Random Forest, and Voting Classifier. We have collected and analysed COVID-19 tweets written in the Arabic language. We used the Hold Out method with different test sizes to split the dataset into training and testing datasets. The obtained results show that the Voting Classifier is the best classifier with a 94.25% accuracy in the test size of 0.5 for the detection of COVID-19 from Arabic tweets.

Downloads

Download data is not yet available.

Downloads

Published

2023-02-14

How to Cite

A. R. Alobaidi, & Z. N. Nuimi. (2023). DETECTING CORONAVIRUS DISEASE OF ARABIC TWEETS USING SENTIMENT ANALYSIS. Journal of Engineering and Technology (JET), 13(2), 81–92. Retrieved from https://jet.utem.edu.my/jet/article/view/6318