Imperial College London
Alternate

Professor Christopher Hankin

Faculty of Engineering, Department of Computing

Professor of Computing
 
 
 
//

Contact

 

c.hankin Website

 
 
//

Location

 

Sherfield BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Hankin:2016:10.1371/journal.pone.0155417,
author = {Hankin, CL and Thapen, N and Simmie, D and Gillard, J},
doi = {10.1371/journal.pone.0155417},
journal = {PLOS One},
title = {DEFENDER: Detecting and Forecasting Epidemics Using Novel Data-Analytics for Enhanced Response},
url = {http://dx.doi.org/10.1371/journal.pone.0155417},
volume = {11},
year = {2016}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - In recent years social and news media have increasingly been used to explain patterns indisease activity and progression. Social media data, principally from the Twitter network,has been shown to correlate well with official disease case counts. This fact has beenexploited to provide advance warning of outbreak detection, forecasting of disease levelsand the ability to predict the likelihood of individuals developing symptoms. In this paper weintroduce DEFENDER, a software system that integrates data from social and news mediaand incorporates algorithms for outbreak detection, situational awareness and forecasting.As part of this system we have developed a technique for creating a location network forany country or region based purely on Twitter data. We also present a disease nowcasting(forecasting the current but still unknown level) approach which leverages counts from multiplesymptoms, which was found to improve the nowcasting accuracy by 37 percent overa model that used only previous case data. Finally we attempt to forecast future levels ofsymptom activity based on observed user movement on Twitter, finding a moderate gain of5 percent over a time series forecasting model.
AU  - Hankin,CL
AU  - Thapen,N
AU  - Simmie,D
AU  - Gillard,J
DO  - 10.1371/journal.pone.0155417
PY  - 2016///
SN  - 1932-6203
TI  - DEFENDER: Detecting and Forecasting Epidemics Using Novel Data-Analytics for Enhanced Response
T2  - PLOS One
UR  - http://dx.doi.org/10.1371/journal.pone.0155417
UR  - http://hdl.handle.net/10044/1/32964
VL  - 11
ER  -
Download