Ensemble learned vaccination uptake prediction using web search queries

Niels Dalum Hansen; Christina Lioma; Kåre Mølbak

doi:10.1145/2983323.2983882

Ensemble learned vaccination uptake prediction using web search queries

Niels Dalum Hansen, Christina Lioma, Kåre Mølbak

Datalogisk Institut

6 Citationer (Scopus)

1 Downloads (Pure)

Abstract

We present a method that uses ensemble learning to combine clinical and web-mined time-series data in order to predict future vaccination uptake. The clinical data is official vaccination registries, and the web data is query frequencies collected from Google Trends. Experiments with official vaccine records show that our method predicts vaccination uptake eff?ectively (4.7 Root Mean Squared Error). Whereas performance is best when combining clinical and web data, using solely web data yields comparative performance. To our knowledge, this is the ?first study to predict vaccination uptake using web data (with and without clinical data).

Originalsprog	Udefineret/Ukendt
Titel	Proceedings of the 25th ACM International Conference on Information and Knowledge Management
Antal sider	4
Forlag	IEEE
Publikationsdato	24 okt. 2016
Sider	1953-1956
ISBN (Elektronisk)	978-1-4503-4073-1
DOI	https://doi.org/10.1145/2983323.2983882
Status	Udgivet - 24 okt. 2016
Begivenhed	25th ACM International Conference on Information and Knowledge Management - Indianapolis, USA Varighed: 24 okt. 2016 → 28 okt. 2016 Konferencens nummer: 25

Konference

Konference	25th ACM International Conference on Information and Knowledge Management
Nummer	25
Land/Område	USA
By	Indianapolis
Periode	24/10/2016 → 28/10/2016

Emneord

cs.IR
stat.AP

FN’s Verdensmål

Dette resultat bidrager til følgende verdensmål

Adgang til dokumentet

10.1145/2983323.2983882

Hansen_2016_EnsembleForlagets udgivne version, 122 KB

Citationsformater

Hansen, ND, Lioma, C & Mølbak, K 2016, Ensemble learned vaccination uptake prediction using web search queries. i Proceedings of the 25th ACM International Conference on Information and Knowledge Management. IEEE, s. 1953-1956, 25th ACM International Conference on Information and Knowledge Management, Indianapolis, USA, 24/10/2016. https://doi.org/10.1145/2983323.2983882

@inproceedings{406ebc68080e4ca6851d20a4c715d7cf,

title = "Ensemble learned vaccination uptake prediction using web search queries",

abstract = "We present a method that uses ensemble learning to combine clinical and web-mined time-series data in order to predict future vaccination uptake. The clinical data is official vaccination registries, and the web data is query frequencies collected from Google Trends. Experiments with official vaccine records show that our method predicts vaccination uptake eff?ectively (4.7 Root Mean Squared Error). Whereas performance is best when combining clinical and web data, using solely web data yields comparative performance. To our knowledge, this is the ?first study to predict vaccination uptake using web data (with and without clinical data).",

keywords = "cs.IR, stat.AP",

author = "Hansen, {Niels Dalum} and Christina Lioma and K{\aa}re M{\o}lbak",

year = "2016",

month = oct,

day = "24",

doi = "10.1145/2983323.2983882",

language = "Udefineret/Ukendt",

pages = "1953--1956",

booktitle = "Proceedings of the 25th ACM International Conference on Information and Knowledge Management",

publisher = "IEEE",

note = "25th ACM International Conference on Information and Knowledge Management ; Conference date: 24-10-2016 Through 28-10-2016",

}

TY - GEN

T1 - Ensemble learned vaccination uptake prediction using web search queries

AU - Hansen, Niels Dalum

AU - Lioma, Christina

AU - Mølbak, Kåre

N1 - Conference code: 25

PY - 2016/10/24

Y1 - 2016/10/24

N2 - We present a method that uses ensemble learning to combine clinical and web-mined time-series data in order to predict future vaccination uptake. The clinical data is official vaccination registries, and the web data is query frequencies collected from Google Trends. Experiments with official vaccine records show that our method predicts vaccination uptake eff?ectively (4.7 Root Mean Squared Error). Whereas performance is best when combining clinical and web data, using solely web data yields comparative performance. To our knowledge, this is the ?first study to predict vaccination uptake using web data (with and without clinical data).

AB - We present a method that uses ensemble learning to combine clinical and web-mined time-series data in order to predict future vaccination uptake. The clinical data is official vaccination registries, and the web data is query frequencies collected from Google Trends. Experiments with official vaccine records show that our method predicts vaccination uptake eff?ectively (4.7 Root Mean Squared Error). Whereas performance is best when combining clinical and web data, using solely web data yields comparative performance. To our knowledge, this is the ?first study to predict vaccination uptake using web data (with and without clinical data).

KW - cs.IR

KW - stat.AP

U2 - 10.1145/2983323.2983882

DO - 10.1145/2983323.2983882

M3 - Konferencebidrag i proceedings

SP - 1953

EP - 1956

BT - Proceedings of the 25th ACM International Conference on Information and Knowledge Management

PB - IEEE

T2 - 25th ACM International Conference on Information and Knowledge Management

Y2 - 24 October 2016 through 28 October 2016

ER -