Thursday, December 20, 2007

What Your Phone Knows About You

MIT's Sandy Pentland finds surprising implications in patterns of cell-phone use.

By Kate Greene

See it all: MIT professor Sandy Pentland is at the forefront of an emerging field called “reality mining,” in which data about people’s activities and interactions--collected by cell phones--could help solve social problems large and small. Credit: Sam Ogden

Multimedia •  Watch a video about Sandy Pentland’s work in sociometrics.

A couple of years ago, Sandy Pentland, professor of media arts and sciences at MIT, handed out about 100 Nokia cell phones to MIT students and faculty. The phones were equipped with software that helped Pentland's team log interactions between the people carrying them. Based on phone calls and the devices' physical proximity to other people's phones (as measured by Bluetooth), Pentland and researcher Nathan Eagle developed social-network models that were more accurate and more nuanced than those constructed from the subjects' self-reports. A paper on the study is currently under review at the journal Nature.

Sifting through cell-phone data to get at the truth of people's social interactions falls under the umbrella of an emerging field that Pentland has dubbed "reality mining." And he thinks that social networks are just the beginning. The same techniques can be applied to other sets of cell-phone data to help people communicate more effectively, manage their time better, and even make their neighborhoods more livable. And it's all thanks to the ubiquity of cell phones--the ultimate data-collection machines.

Technology Review caught up with Pentland to ask him about reality mining and its implications.

Technology Review: When you talk about reality mining, what do you mean?

Sandy Pentland: The real roots of it go back to early 1990s, when people first started talking about context-aware computing. Just look at a cell phone. It knows where you are, and this is obviously sort of useful. But the generalization is that maybe it can know lots of things about you. Take your Facebook friends as an example. The phone could know which ones you socialize with in person, which ones are your work friends, and which friends you've never seen in your life. That's an interesting distinction, and reality mining can make it automatic. It's about making the "dumb" information-technology infrastructure know something about your social life. All this sort-of Web 2.0 stuff is nice, but you have to type stuff in. Things are never up to date, and unless you consciously know about something, you can't put it in. Reality mining is all about paying attention to patterns in life and using that information to help you do things like set privacy policies, share things with people, notify people when you're near them, and just to help you live your life.

TR: What technologies are enabling reality mining now?

SP: Today's cell phones are on us all the time, and they come with hardware that can act as sensors for your environment. For instance, if Bluetooth is turned on, then the phone can see and be seen by other Bluetooth devices. You can start to make a record of the Bluetooth-enabled devices you encounter throughout the day. Then you can figure out, based on the frequency [with which] you encounter other people's Bluetooth phones, what sort of relationship you have with them.

The iPhone also has an accelerometer that could tell if you are sitting and walking. You don't have to explicitly type stuff in; it's just measured. And all phones have built-in microphones that can be used to analyze your tone of voice, how long you talk, how often you interrupt people. These patterns can tell you what roles people play in groups: you can figure out who the leader is and who the followers are. It's folk psychology, and some of the stuff people may already know, but we haven't been able to measure it, at such a large scale, before these phones.