Online Searches as Early Warning Indicators of Conflict?

It was after watching Larry Brilliant’s 2006 TED presentation on the Global Public Health Information Network (GPHIN) that I realized just how far behind we are (in the conflict early warning community) vis-a-vis adopting new information communication technologies and digital methods. I therefore chose to teach a full-semester seminar in Fall 2006 entitled “From Disaster to Conflict Early Warning/Response” to demonstrate what we can learn from the disaster management community, not least vis-a-vis the creative use of technology.

The reason I got exited about GPHIN was because I immediately thought about possible applications for conflict early warning systems (CEW). I therefore co-authored a paper on this topic with Adam White, one of my students that Fall. Here is a short excerpt:


Two years hence, Google has found that certain search terms are good indicators of flu activity. Indeed, “Google Flu Trends” uses “aggregated Google Search data to estimate flu activity in your state up to two weeks faster than traditional flu surveillance systems.”

We have found a close relationship between how many people search for flu-related topics and how many people actually have flu symptoms. Of course, not every person who searches for “flu” is actually sick, but a pattern emerges when all the flu-related search queries from each state and region are added together.

See the dynamic time series below. The blue curve represents Google’s monitoring of search terms while the yellow curve are the actual data on outbreaks of the flu as reported by the CDC:

Together with the map:


I find this a truly fascinating study and wonder how effective the methodology might be if we were to apply it to monitor conflict, social tensions, etc?


5 responses to “Online Searches as Early Warning Indicators of Conflict?

  1. Pingback: Security Provoked » Blog Archive » Early Warnings Ignored in Mumbai Attack

  2. Pingback: Web4Dev: Innovation Track Day 1 « iRevolution

  3. Pingback: Detecting Rumors with Web-based Text Mining System « Conflict Early Warning and Early Response

  4. Pingback: iRevolution One Year On… « iRevolution

  5. Pingback: Conflict Early Warning Blog: One Year On « Conflict Early Warning and Early Response

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s