Cross-Linguistic Twitter Analysis of Discussion Themes before, during and after Ramadan

Aamna Alshehhi, Justin Thomas, Roy Welsch, Zeyar Aung

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageBritish English
Title of host publication2019 4th IEEE International Conference on Big Data Analytics, ICBDA 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages73-78
Number of pages6
ISBN (Electronic)9781728112824
DOIs
StatePublished - 10 May 2019
Event4th IEEE International Conference on Big Data Analytics, ICBDA 2019 - Suzhou, China
Duration: 15 Mar 201918 Mar 2019

Publication series

Name2019 4th IEEE International Conference on Big Data Analytics, ICBDA 2019

Conference

Conference4th IEEE International Conference on Big Data Analytics, ICBDA 2019
Country/TerritoryChina
CitySuzhou
Period15/03/1918/03/19

Keywords

  • Arabic tweets
  • big data
  • lda
  • ramadan
  • topic modeling
  • twitter
  • UAE

Fingerprint

Dive into the research topics of 'Cross-Linguistic Twitter Analysis of Discussion Themes before, during and after Ramadan'. Together they form a unique fingerprint.

Cite this