Google Flu Trends Still Appears Sick: An Evaluation of the 2013-2014 Flu Season

11 Pages Posted: 14 Mar 2014  

David Lazer

Northeastern University - Department of Political Science; Harvard University - Harvard Kennedy School (HKS)

Ryan Kennedy

University of Houston - Department of Political Science

Gary King

Harvard University

Alessandro Vespignani

Northeastern University

Date Written: March 13, 2014

Abstract

In response to its poor performance during the 2012-2013 flu season, Google Flu Trends (GFT) engineers announced a redesign of the GFT algorithm. Two changes were made: (1) dampening anomalous media spikes and (2) using ElasticNet, rather than regression, for estimation. This paper identifies several problems that persist in the new algorithm. First, the transparency problems identified in our earlier Science paper appear to have, if anything, become worse. Second, there are reasons to doubt whether a spike in media attention was the only, or primary, cause of GFT's errors. Finally, there is strong evidence that GFT is still not using all the information at its disposal to make accurate measurements of flu prevalence. While it is too early to give a complete evaluation of the new algorithm, these results are discouraging.

Keywords: Google Flu Trends, big data, transparency, replication, time series

JEL Classification: C22, I1, I18

Suggested Citation

Lazer, David and Kennedy, Ryan and King, Gary and Vespignani, Alessandro, Google Flu Trends Still Appears Sick: An Evaluation of the 2013-2014 Flu Season (March 13, 2014). Available at SSRN: https://ssrn.com/abstract=2408560 or http://dx.doi.org/10.2139/ssrn.2408560

David Lazer

Northeastern University - Department of Political Science ( email )

Boston, MA 02115
United States
617-373-2796 (Phone)
617-373-5311 (Fax)

Harvard University - Harvard Kennedy School (HKS) ( email )

79 John F. Kennedy Street
Taubman Center
Cambridge, MA 02138
United States
617-496-0102 (Phone)
617-496-1722 (Fax)

HOME PAGE: http://www.davidlazer.com

Ryan Kennedy (Contact Author)

University of Houston - Department of Political Science ( email )

TX 77204-3011
United States
713-743-1663 (Phone)
713-743-3890 (Fax)

Gary King

Harvard University ( email )

1737 Cambridge St.
Institute for Quantitative Social Science
Cambridge, MA 02138
United States
617-500-7570 (Phone)

HOME PAGE: http://gking.harvard.edu

Alessandro Vespignani

Northeastern University ( email )

Boston, MA 02115
United States

Paper statistics

Downloads
610
Rank
34,151
Abstract Views
5,385