Accepted for/Published in: JMIR Infodemiology
Date Submitted: Oct 7, 2023
Open Peer Review Period: Aug 21, 2024 - Oct 16, 2024
Date Accepted: Dec 8, 2024
(closed for review but you can still tweet)
Unveiling Topics and Emotions in Arabic Tweets Surrounding the COVID-19 Pandemic: A Topic Modeling and Sentiment Analysis Approach
ABSTRACT
Background:
Background:
The worldwide effects of the COVID-19 pandemic have been deeply profound, and the Arab world has not been exempt from its wide-ranging consequences. Within this context, social media platforms like Twitter have taken on a crucial role as vital sources for sharing information and expressing public opinions during this global crisis. Careful investigation of Arabic tweets related to COVID-19 can provide invaluable insights into the common topics and underlying sentiments that shape discussions about the pandemic.
Objective:
Objective:
The objective of the present study was to understand the concerns and feelings of Twitter users in the Arabic speaking countries about the COVID-19 pandemic. This was accomplished through analyzing the themes and sentiments that were expressed in Arabic tweets about the pandemic.
Methods:
Methods:
In this study, 1 million Arabic tweets related to COVID-19 and posted between March 1 and March 31, 2020, were analyzed. Machine learning techniques, such as topic modeling and sentiment analysis, were applied to understand the main topics and emotions that were expressed in these tweets.
Results:
Results:
The analysis of Arabic tweets revealed several prominent topics related to COVID-19. The analysis identified and grouped 16 different conversation topics that were organized into 8 themes : (1) Preventive Measures and Safety, (2) Medical and Healthcare Aspects, (3) Government and Social Measures, (4) Impact and Numbers, (5) Vaccine Development and Research, (6) COVID-19 and Religious Practices, (7) COVID19’s Global Impact on Sports and Countries, and (8) COVID-19 and National Efforts. Across all the topics we identified, the prevailing sentiments regarding the spread of COVID-19 were primarily centered around anger, followed by disgust, joy, and anticipation. Notably, when conversations revolved around new COVID-19 cases and fatalities, public tweets revealed a notably heightened sense of anger in comparison to other subjects.
Conclusions:
Conclusions:
The study provides valuable insights into the topics and emotions associated with COVID-19 as reflected in Arabic tweets. It demonstrates the significance of social media platforms, particularly Twitter, in capturing the Arab speaking community’s concerns and sentiments during the pandemic. The findings contribute to a deeper understanding of the prevailing discourse, enabling take holders to tailor effective communication strategies and address specific public concerns. This study underscores the importance of monitoring social media conversations in Arabic to support public health efforts and crisis management during the COVID-19 pandemic.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.