DIM 11.09 - Tommaso Venturini, médialab SciencesPo

DIM 11.09 - Tommaso Venturini, médialab SciencesPo

• 1.
   
• 2.
  HOW ? Byprocessing hundreds of billions of individual searches from 5 years (2003-2008) of Google search logs To track influenza-like illness in a population.
• 3.
  PREVIOUS ATTEMPS Queries to a Swedish medical website Visitors to pages on a U.S. health website User clicks on a advertisement in Canada A set of Yahoo search queries
• 4.
  HOW EXACTLY ?Automated method of selecting queries: 50 million queries separately Sets of N top scoring queries Combining the N=45 highest-scoring queries was found to obtain the best fit.
• 5.
  MEAN CORRELATION 0.97
• 6.
   
• 7.
  Texte
• 8.
  Texte
• 9.
   
• 10.
  J. S. Brownstein,C. Freifeld, C. Madoff, 2009 “ Digital Disease Detection” New England Journal of Medicine 360, no. 21
• 11.
  Jurgen Doornik 2009“ Improving the Timeliness of Data on Influenza-like Illnesses using Google Search Data” (unpublished)
• 12.
  Hyunyoung Choi andHal Varian, 2009 “Predicting the Present with Google Trends” http://googleresearch.blogspot.com
• 13.
  N. Askitas andK. Zimmermann, 2009 “Google Econometrics and Unemployment Forecasting.”
• 14.
  G. K., Webb,2009 "Forecasting U.S. Home Foreclosures with an Index of Internet Keyword Searches" In Value Creation in E-Business Management
• 15.
  J. Azar, 2009"Electric Cars and Oil Prices" SSRN eLibrary  
• 16.
  Laura Granka 2009"Inferring the Public Agenda from Implicit Query Data" Proceeding SIGIR 2009
• 17.
  M. Scharkow /J. Vogelgesang, 2009 "Google Insights for Search: A Methodological Innovation in the Study of the Public Agenda? » DGPuK Conference
• 18.
  Yair Shimshoni NivEfron Yossi Matias, 2009 "On the Predictability of Search Trends" Google, Israel Labs
• 19.
  R. Karthik, A.Rachakonda, S. Srinivasa, 2008 "Query Heartbeat" In proceeding of COMAD