?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Transfer+learning+for+unsupervised+influenza-like+illness+models+from+online+search+data&rft.creator=Zou%2C+B&rft.creator=Lampos%2C+V&rft.creator=Cox%2C+I&rft.description=A+considerable+body+of+research+has+demonstrated+that+online%0D%0Asearch+data+can+be+used+to+complement+current+syndromic+surveillance+systems.+The+vast+majority+of+previous+work+proposes+solutions+that+are+based+on+supervised+learning+paradigms%2C+in+which%0D%0Ahistorical+disease+rates+are+required+for+training+a+model.+However%2C%0D%0Afor+many+geographical+regions+this+information+is+either+sparse+or%0D%0Anot+available+due+to+a+poor+health+infrastructure.+It+is+these+regions%0D%0Athat+have+the+most+to+benefit+from+inferring+population+health+statistics+from+online+user+search+activity.+To+address+this+issue%2C+we%0D%0Apropose+a+statistical+framework+in+which+we+first+learn+a+supervised+model+for+a+region+with+adequate+historical+disease+rates%2C+and%0D%0Athen+transfer+it+to+a+target+region%2C+where+no+syndromic+surveillance%0D%0Adata+exists.+This+transfer+learning+solution+consists+of+three+steps%3A%0D%0A(i)+learn+a+regularized+regression+model+for+a+source+country%2C+(ii)%0D%0Amap+the+source+queries+to+target+ones+using+semantic+and+temporal+similarity+metrics%2C+and+(iii)+re-adjust+the+weights+of+the+target%0D%0Aqueries.+It+is+evaluated+on+the+task+of+estimating+influenza-like+illness+(ILI)+rates.+We+learn+a+source+model+for+the+United+States%2C+and%0D%0Asubsequently+transfer+it+to+three+other+countries%2C+namely+France%2C%0D%0ASpain+and+Australia.+Overall%2C+the+transferred+(unsupervised)+models%0D%0Aachieve+strong+performance+in+terms+of+Pearson+correlation+with%0D%0Athe+ground+truth+(%3E+.92+on+average)%2C+and+their+mean+absolute+error%0D%0Adoes+not+deviate+greatly+from+a+fully+supervised+baseline.&rft.publisher=ACM&rft.date=2019-05-12&rft.type=Proceedings+paper&rft.language=eng&rft.source=+++++In%3A++Proceeding+WWW+'19+The+World+Wide+Web+Conference.++(pp.+pp.+2505-2516).++ACM%3A+San+Francisco%2C+CA%2C+USA.+(2019)+++++&rft.format=text&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10074319%2F1%2Fp2505-zou.pdf&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10074319%2F&rft.rights=open