Skip to main content
Article
Cross-Linguistic Twitter Analysis of Discussion Themes before, during and after Ramadan
2019 4th IEEE International Conference on Big Data Analytics, ICBDA 2019
  • Aamna Alshehhi, Khalifa University of Science and Technology
  • Justin Thomas, Zayed University
  • Roy Welsch, MIT Sloan School of Management
  • Zeyar Aung, Zayed University
Document Type
Conference Proceeding
Publication Date
5-10-2019
Abstract

© 2019 IEEE. This study represents the first comprehensive analysis of Twitter data for the United Arab Emirates using both Arabic and English texts. Particular attention is given to the impact of the holy period of Ramadan on the thematic content of Twitter discourse. We examine users' tweet frequency, tweet length and tweet content for different languages (English/Arabic) using statistical methods and topic modeling. The results indicate that Arabic language tweets, during the Ramadan period, included more religious themes than did English tweets. Also, relative to English, Arabic tweets showed greater consistency of content during the three months of the study (before, during and after Ramadan). English content varied significantly over the three months with notable fluctuations in the frequency of content centering on the music, shopping, and health categories. These results suggest that such analytic methods applied to social media data can provide a useful indicator of societal discussion themes. Further research is merited with larger datasets over longer timeframes.

ISBN
9781728112824
Publisher
Institute of Electrical and Electronics Engineers Inc.
Keywords
  • Arabic tweets,
  • big data,
  • lda,
  • ramadan,
  • topic modeling,
  • twitter,
  • UAE
Scopus ID
85066608754
Indexed in Scopus
Yes
Open Access
No
https://doi.org/10.1109/ICBDA.2019.8712840
Citation Information
Aamna Alshehhi, Justin Thomas, Roy Welsch and Zeyar Aung. "Cross-Linguistic Twitter Analysis of Discussion Themes before, during and after Ramadan" 2019 4th IEEE International Conference on Big Data Analytics, ICBDA 2019 (2019) p. 73 - 78
Available at: http://works.bepress.com/justin-thomas28211/23/