Time-Series Adaptive Estimation of Vaccination Uptake Using Web Search Queries
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
Time-Series Adaptive Estimation of Vaccination Uptake Using Web Search Queries. / Dalum Hansen, Niels; Mølbak, Kåre; Cox, Ingemar J.; Lioma, Christina.
Proceedings of the 26th International Conference on World Wide Web Companion. International World Wide Web Conferences Steering Committee, 2017. s. 773-774.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Time-Series Adaptive Estimation of Vaccination Uptake Using Web Search Queries
AU - Dalum Hansen, Niels
AU - Mølbak, Kåre
AU - Cox, Ingemar J.
AU - Lioma, Christina
PY - 2017
Y1 - 2017
N2 - Estimating vaccination uptake is an integral part of ensuring publichealth. It was recently shown that vaccination uptake can beestimated automatically from web data, instead of slowly collectedclinical records or population surveys [2]. All prior work in thisarea assumes that features of vaccination uptake collected fromthe web are temporally regular. We present the first ever methodto remove this assumption from vaccination uptake estimation:our method dynamically adapts to temporal fluctuations in timeseries web data used to estimate vaccination uptake. We showour method to outperform the state of the art compared tocompetitive baselines that use not only web data but also curatedclinical data. This performance improvement is more pronouncedfor vaccines whose uptake has been irregular due to negativemedia attention (HPV-1 and HPV-2), problems in vaccine supply(DiTeKiPol), and targeted at children of 12 years old (whosevaccination is more irregular compared to younger children).
AB - Estimating vaccination uptake is an integral part of ensuring publichealth. It was recently shown that vaccination uptake can beestimated automatically from web data, instead of slowly collectedclinical records or population surveys [2]. All prior work in thisarea assumes that features of vaccination uptake collected fromthe web are temporally regular. We present the first ever methodto remove this assumption from vaccination uptake estimation:our method dynamically adapts to temporal fluctuations in timeseries web data used to estimate vaccination uptake. We showour method to outperform the state of the art compared tocompetitive baselines that use not only web data but also curatedclinical data. This performance improvement is more pronouncedfor vaccines whose uptake has been irregular due to negativemedia attention (HPV-1 and HPV-2), problems in vaccine supply(DiTeKiPol), and targeted at children of 12 years old (whosevaccination is more irregular compared to younger children).
U2 - 10.1145/3041021.3054251
DO - 10.1145/3041021.3054251
M3 - Article in proceedings
SN - 978-1-4503-4914-7
SP - 773
EP - 774
BT - Proceedings of the 26th International Conference on World Wide Web Companion
PB - International World Wide Web Conferences Steering Committee
T2 - 26th International Conference on World Wide Web Companion
Y2 - 3 April 2017 through 7 April 2017
ER -
ID: 197766822