Worldwide Influenza Surveillance through Twitter

Michael J. Paul, Mark Dredze, David A. Broniatowski, Nicholas Generous

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We evaluate the performance of Twitter-based influenza surveillance in ten English-speaking countries across four continents. We find that tweets are positively correlated with existing surveillance data provided by government agencies in these countries, with r values ranging from .37-81. We show that incorporating Twitter data into a strong autoregressive baseline reduces mean squared error in 80 to 100 percent of locations depending on the lag, with larger improvements when reporting delays are longer.

Original languageEnglish (US)
Title of host publicationThe World Wide Web and Public Health Intelligence - Papers Presented at the 29th AAAI Conference on Artificial Intelligence, Technical Report
PublisherAI Access Foundation
Pages6-11
Number of pages6
ISBN (Electronic)9781577357261
StatePublished - 2015
Externally publishedYes
Event29th AAAI Conference on Artificial Intelligence, AAAI 2015 - Austin, United States
Duration: Jan 25 2015Jan 30 2015

Publication series

NameAAAI Workshop - Technical Report
VolumeWS-15-15

Conference

Conference29th AAAI Conference on Artificial Intelligence, AAAI 2015
Country/TerritoryUnited States
CityAustin
Period1/25/151/30/15

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Worldwide Influenza Surveillance through Twitter'. Together they form a unique fingerprint.

Cite this