Using a Rule-based Model to Detect Arabic Fake News Propagation during Covid-19

Since the emergence of the Covid-19, both factual and false information about the new virus has been disseminated. Fake news harms societies and must be combated. This research aims to identify Arabic fake news tweets and classify them into six categories: entertainment, health, politics, religious, social, and sports. The study also aims to uncover patterns in the spread of Arabic fake news associated with the Covid-19 pandemic. The researchers created an Arabic dictionary and used text classification based on a rule-based system to detect and categorize fake news. A dataset consisting of 5 million tweets was analyzed. The developed model achieves an overall accuracy of 78.1% with 70% precision and 98%recall. The model detected more than 26006 fake news tweets. Interestingly we found an association between the number of fake news tweets and dates. The result demonstrates that as more information and knowledge about Covid-19 become available over time, people's awareness increase, while the number of fake news tweets decreases. The categorization of false news indicates that the social category was highest in all Arab countries except Palestine, Qatar, Yemen, and Algeria. Conversely, fake news related to the entertainment category was the weakest dissemination in most Arab countries.

@article{Alotaibi2022,
  title     = {Using a Rule-based Model to Detect Arabic Fake News Propagation during Covid-19},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {13},
  number    = {1},
  year      = {2022},
  publisher = {The Science and Information Organization},
  author    = {Fatimah L. Alotaibi and Muna M. Alhammad},
  doi       = {10.14569/IJACSA.2022.0130114},
  url       = {https://doi.org/10.14569/IJACSA.2022.0130114}
}