Can Social Web Help to Detect Influenza Related Illnesses in Turkey?


BİLGE U., Bozkurt S., Yolcular B. O., Ozel D.

Special Topic Conference of the European-Federation-for-Medical-Informatics (EFMI), Moscow, Russia, 18 - 20 April 2012, vol.174, pp.100-104 identifier identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 174
  • Doi Number: 10.3233/978-1-61499-052-9-100
  • City: Moscow
  • Country: Russia
  • Page Numbers: pp.100-104
  • Keywords: Social media, twitter, influenza like illnesses, flu epidemic, HEALTH
  • Akdeniz University Affiliated: Yes

Abstract

In this study, a content analysis of Twitter is carried out to determine the frequency of tweets mentioning influenza like illnesses (swine flu, cold etc.) and results have been compared with news articles, Google search trends and national health statistics in Turkey. Between 1st January 2009 and 31st December 2010, over 4,165 influenza-related Turkish posts on Twitter and 10,000 news articles in three leading Turkish newspaper websites containing influenza related keywords have been analyzed. No strong correlation has been found between influenza related online data and the real world records. Although there is no significant relationship, this study shows that there is a huge amount of data can be harvested from the social web applications such as Twitter.