The life and death of Google Flu Trends

Posted by seventyhorses on Tuesday November 05, 2019 @03:55PM
from the medanthrotheory.org dept.

http://www.medanthrotheory.org/read/11446/algorithmic-futures

( 3 comments | 14 points | on HN )

Re:The life and death of Google Flu Trends by nl on Tuesday November 05, 2019 @07:04PM (#21458341)

This neglects to mention the follow-up work Google did on Flu Trends, where they corrected for media and "online" interest and made it work again.

https://www.ncbi.nlm.nih.gov/pubmed/26234783

[ Parent | on HN ]

Re:The life and death of Google Flu Trends by jarfil on Tuesday November 05, 2019 @08:02PM (#21458718)

They correct the predictions for past data, but I'm sceptical as to whether it's possible to correct for emerging feedback loops when the results of the analysis are public and cause a change in the behavior patterns being analyzed.

[ Parent | on HN ]

Re:The life and death of Google Flu Trends by nl on Tuesday November 05, 2019 @08:53PM (#21458981)

Well they stopped the analysis being public too.

Instead they release it to other groups who use it as a single combined with others for predictions.

[ Parent | on HN ]