Your Social Forecaster

This short article in Wired UK this month is a good read.

"How do fads spread through a community?" asks Alex Pentland, director of MIT's Human Dynamics Laboratory in Cambridge, Massachusetts. "I'd often wondered, so over the years I've built a series of platforms that come closer to the God's-eye view of what happens." The latest, which he calls Social fMRI, allows him to understand and predict how social patterns spread, from political views to obesity.

Last year, Pentland, 60, gave more than 130 participants Android phones containing an app, funf, developed by Nadav Aharony, a PhD student at the MIT Media Lab. funf tracks the minutiae of their social interactions. Phone conversations are logged; SMS and email trails stored; interactions across Facebook monitored.

Using machine-learning algorithms to predict trend adoption, Pentland can forecast when individuals will install new smartphone apps, spend money or even take up new exercise regimes. All that's required is the history of social interactions between group members. "When you provide something new to a community, such as a smartphone app, the wave of adoption is pushed purely by social interactions," he explains. "We decide things not through logic, but through interactions."

Pentland is a firm believer in the power social groups have in influencing opinion - even over contentious issues such as war and politics. "There are a lot of things left for us to do," says Pentland. "But some of them might make the world a much better place."