Topic Discovery on Farsi, English, French, and Arabic Tweets Related to COVID-19 Using Text Mining Techniques

Stud Health Technol Inform. 2021 May 7:279:26-33. doi: 10.3233/SHTI210084.

Abstract

Background: Social networks are a good source for monitoring public health during the outbreak of COVID-19, these networks play an important role in identifying useful information.

Objectives: This study aims to draw a comparison of the public's reaction in Twitter among the countries of West Asia (a.k.a Middle East) and North Africa in order to make an understanding of their response regarding the same global threat.

Methods: 766,630 tweets in four languages (Arabic, English French, and Farsi) tweeted in March 2020, were investigated.

Results: The results indicate that the only common theme among all languages is "government responsibilities (political)" which indicates the importance of this subject for all nations.

Conclusion: Although nations react similarly in some aspects, they respond differently in others and therefore, policy localization is a vital step in confronting problems such as COVID-19 pandemic.

Keywords: COVID-19; Epidemics; Natural Language Processing; Social Networking.

MeSH terms

  • Asia
  • COVID-19*
  • Data Mining
  • Humans
  • Language
  • Middle East
  • Pandemics
  • SARS-CoV-2
  • Social Media*