Human behavior, through the lens of a smartphone

The proliferation of smartphones is allowing scientists to capture an unprecedented amount of information about people -- that in aggregate, offers us insights into how we live, work and play.

We all know that smartphones track a wealth of personal data, from location to private messages to contact lists and more.

But what if, at large scale, they could tell us about human behavior?

That's according to a Wall Street Journal report from this weekend, which suggests that -- privacy issues aside -- the ability to record movements, relationships, moods, spending and other habits has revealed patterns in human behavior that allow scientists to better understand us.

For example, with mobile data scientists can:

  • ...determine "influencers," people who are likely to cause others to change their minds.
  • ...predict where people are likely to be at a given time.
  • ...predict movement in the Dow Jones Industrial Average.
  • ...chart the spread of political ideas through a community.
  • ...reveal symptoms of mental illness.

And, of course, mobile operators can predict -- based on a user's social circle of friends -- which people are most likely to defect to other carriers, which may help explain why a T-Mobile representative called me out of the blue last month to see how happy I was with my service.

(All this from the data captured by calls, motion sensor, proximity sensor, ambient light sensor, cameras, compass, gyroscope and accelerometer.)

At the center of this research is Alex Pentland, director of the Human Dynamics Laboratory at the Massachusetts Institute of Technology. The good news? Mining mobile data provides a kind of granular insight that can -- used appropriately -- help officials improve public health, urban planning and marketing just by better understanding the situation at hand.

Robert Lee Hotz reports:

The current work builds on his earlier experiments, beginning in 2004, conducted in an MIT dormitory that explored how relationships influence behavior, health, eating habits and political views. Dr. Pentland and his colleagues used smartphones equipped with research software and sensors to track face-to-face encounters among 78 college students in a dorm during the final three months of the 2008 presidential election.

Every six minutes, each student's phone scanned for any other phone within 10 feet, as a way to identify face-to-face meetings. Among other things, each phone also reported its location and compiled an anonymous log of calls and text messages every 20 minutes. All told, the researchers compiled 320,000 hours of data about the students' behavior and relationships, buttressed by detailed surveys.


Almost a third of the students changed their political opinions during the three months. Their changing political ideas were related to face-to-face contact with project participants of differing views, rather than to friends or traditional campaign advertising, the analysis showed.

Amazing stuff, and well worth the full read.

The Really Smart Phone [WSJ]

This post was originally published on