Reality Mining, or what your cellphone knows about you

Some years ago MIT’s Professor Sandy Pentland was working on biosensors. A marathon runner, he had sensors built into his footwear which monitored his physical condition from the moment he put them on. In a short MIT video (which I can’t find on the Web any more) he came up with a classic one-liner: “Your shoes may know more about you than your doctor does”.

The idea behind this research is automatically gathering and aggregating data from an individual’s activities to create useful knowledge. Now, Pentland and co-workers are about to publish a paper (Eagle, Pentland & Lazer, in submission) describing research based on detailed data gathered from specially adapted mobile phones issued to a hundred MIT students and staff. MIT’s Technology Review explains that the researchers collected data not just on who called whom, but also on close encounters – using Bluetooth, the phones detected when they were physically near to another phone in the trial. Out of this, for example, it’s possible to determine who are people’s close work colleagues, who their social contacts, and so on.

Prof. Pentland says this work falls under the umbrella of an emerging field: “reality mining”. Social networks such as Facebook are part of it too, but your network on Facebook or LinkedIn is something you develop with a lot of manual intervention. Reality mining could allow this to be taken care of automatically.

And there’s more that the next generation of cellphones can detect. As Pentland puts it:

The iPhone … 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 [could] 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.

Does this scare you? Sandy Pentland is alive to the privacy and surveillance issues, and acknowledges their significance; but he also has counter-examples of possible applications for considerable social benefit. For example: if one morning no-one in your network is coming to work, might this give early warning of a major epidemic? Like all technologies, reality mining could be used in either way. It’s up to professionals to highlight the issues as well as to develop the possibilities.


What your phone knows about you (MIT Technology Review, 20 Dec 2007)
Reality Mining at MIT Media Lab: click “Publications” for published papers

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