PLOS Computational Biology: Wikipedia Usage Estimates Prevalence of Influenza-Like Illness in the United States in Near Real-Time
▻http://www.ploscompbiol.org/article/info%3Adoi%2F10.1371%2Fjournal.pcbi.1003581
We introduce a novel method of estimating, in near-real time, the level of influenza-like illness (ILI) in the United States (US) by monitoring the rate of particular Wikipedia article views on a daily basis. We calculated the number of times certain influenza- or health-related Wikipedia articles were accessed each day between December 2007 and August 2013 and compared these data to official ILI activity levels provided by the Centers for Disease Control and Prevention (CDC). We developed a Poisson model that accurately estimates the level of ILI activity in the American population, up to two weeks ahead of the CDC, with an absolute average difference between the two estimates of just 0.27% over 294 weeks of data. Wikipedia-derived ILI models performed well through both abnormally high media coverage events (such as during the 2009 H1N1 pandemic) as well as unusually severe influenza seasons (such as the 2012–2013 influenza season). Wikipedia usage accurately estimated the week of peak ILI activity 17% more often than Google Flu Trends data and was often more accurate in its measure of ILI intensity.
Extrait de l’abstract, la totalité de l’article est disponible. Dont ce graphique (_on est meilleur que #Google_Flu_trends…)
Figure 1. Time series plot of CDC ILI data versus estimated ILI data.
(A) Wikipedia Full Model (Mf) accurately estimated 3 out of 6 ILI activity peaks and had a mean absolute difference of 0.27% compared to CDC ILI data. (B) Wikipedia Lasso Model (Ml) accurately estimated 2 out of 6 ILI activity peaks and had a mean absolute difference of 0.29% compared to CDC ILI data,. (C) Google Flue Trends (GFT) model accurately estimated 2 of 6 ILI activity peaks and had a mean absolute difference of 0.42% compared to CDC ILI data.