Content Analysis of Syndromic Twitter Data

Authors

  • Bethany Keffala Linguistics, University of California, San Diego
  • Mike Conway University of California, San Diego - Division of Biomedical Informatics
  • Son Doan University of California, San Diego - Division of Biomedical Informatics
  • Nigel Collier National Institute of Informatics

DOI:

https://doi.org/10.5210/ojphi.v5i1.4548

Abstract

We present the results of a content analysis of tweets related to respiratory syndrome. An annotation scheme was developed to differentiate between true positive and false positive tweets, and to quantify more fine-grained information about the content of the tweets. This annotation scheme is general, and as such can be used to aid in surveillance of different syndromes. In addition to finding good separation between true and false positive tweets, results showed that users referencing respiratory syndrome were more likely to discuss their own, current experience than they were to reference another person's symptoms or symptoms not currently being experienced, that expressed sentiment was largely negative, and that there was significant use of expressions of aspiration or hyperbole.

Author Biography

Bethany Keffala, Linguistics, University of California, San Diego

Bethany Keffala is a PhD student in Linguistics at the University of California, San Diego, where she studies phonological acquisition, bilingualism, and psycholinguistics.

Downloads

Published

2013-03-23

How to Cite

Keffala, B., Conway, M., Doan, S., & Collier, N. (2013). Content Analysis of Syndromic Twitter Data. Online Journal of Public Health Informatics, 5(1). https://doi.org/10.5210/ojphi.v5i1.4548

Issue

Section

Poster Presentations