Skip to Content

Smart Badges Track Human Behavior

MIT researchers used conference badges to collect data on people’s interactions and visualize the social network.
January 30, 2008

In the corporate and academic worlds, conferences and networking events are necessary. But while some people trade business cards with aplomb, others clump with coworkers, rarely venturing beyond the safety of their pre-existing social circle. New research from MIT’s Media Lab has shown that a sensor-laden conference badge might be able to help people venture out, form new connections, and gain insight into how they interact with others at such events.

Social sense: MIT researchers tracked people’s social interactions at a conference using a smart badge (top) that incorporated an infrared sensor, wireless radio, accelerometer, and microphone to log people’s behaviors. The result was a social network (bottom), produced in real time, which showed who had spoken to whom during the course of the event.

Ben Waber, an MIT researcher who worked on the project (and blogged about it here), gave souped-up badges to 70 participants at a Media Lab event. These badges use an infrared sensor to gather data about face-to-face interactions, a wireless radio to collect data regarding proximity to other badges and send it to a central computer, an accelerometer to track motion of the participant, and a microphone to monitor speech patterns. At the event, the data from the infrared sensors was wirelessly transmitted to a computer that crunched the numbers, producing a real-time visualization of the event’s social graph.

This project illustrates the increasing popularity of sociometrics, a discipline in which sensors collect fine-grained data during social interactions and software makes sense of it. Waber works with MIT professor Sandy Pentland, who is credited with much of the early work in sociometrics and coining the term “reality mining.” (See “What Your Cell Phone Knows About You” and “The iPhone’s Untapped Potential.”) But Waber and Pentland aren’t alone. Researchers at Intel are using sensors to help monitor the health and behavior of the elderly. And others are using position data gleaned from cell phones to help develop more-comprehensive models of how disease spreads.

In addition, an MIT spin-off company, nTag, provides smart badges similar to Waber’s that automatically send out and receive “e-cards.” While nTag’s badges don’t collect motion and voice data, they are capable displaying data as real-time visualizations of the social network at a conference, says Rick Borovoy, cofounder and chief technology office of the company.

Borovoy says that revealing a social network, in particular, can change the dynamics at a conference. “It creates a sense of community and identity, and it’s a way to subtly intervene and disrupt conventional networking patterns,” he says. Borovoy says that nTag has found that showing people their networking patterns on a social graph is enough to change them. “You think people know their patterns, but often they don’t,” he says.

Waber says that the smart badges used in his experiment, which are about the size of a deck of cards but weigh less, can do more than just show face-to-face interactions and display a real-time social graph, and he has plans to look at the rest of the data to see what patterns emerge. For example, since the wireless radio can sense proximity and voice data, it’s possible to infer when a person is engaged in a group discussion and who the expert is.

Also, accelerometer data could indicate activity at the conference. Waber says that if a conference organizer is running around, it could indicate that he needs help getting things done. This could indicate that the organizer should plan for more help at certain times during an event.

Some experts suspect that, within the next few years, smart badges won’t be confined to conferences and events. “We think that eventually everyone will have a smart badge with them all the time: their cell phone,” says Alex Kass, a researcher who leads reality-mining projects at Accenture, a technology firm. “Cell phones will transmit some kind of identity or interesting information to the people around you; you’ll decide certain aspects of your identity that you want to broadcast in public,” he says.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at with a list of newsletters you’d like to receive.