TR10: Reality Mining
(Page 2 of 2)
This relationship information could have much broader implications. Earlier this year, Nathan Eagle, a former MIT grad student who had led the reality-mining research in Pentland's lab, moved to the Santa Fe Institute in New Mexico. There, he plans to use cell-phone data to improve existing computational models of how diseases like SARS spread. Most epidemiology models don't back up their predictions with detailed data on where and with whom people spend their time, Eagle says. The addition of relationship and proximity data would make these models more accurate. "What's interesting is that you can see that a disease spreads based on who is infected first," Eagle says.
Taking advantage of other sensors in cell phones, such as the microphone or the accelerometers built into newer devices like Apple's iPhone, could even extend the benefits of reality mining into personal health care, Pentland says. For example, clues to diagnosing depression could be found in the way a person talks: depressed people may speak more slowly, a change that speech analysis software on a phone might recognize more readily than friends or family do. Monitoring a phone's motion sensors might reveal slight changes in gait, which could be an early indicator of ailments such as Parkinson's disease.
While the promise of reality mining is great, the idea of collecting so much personal information naturally raises many questions about privacy, Pentland admits. He says it's crucial that behavior-logging technology not be forced on anyone. But legal statutes are lagging behind our data collection abilities, he says, which makes it all the more important to begin discussing how the technology will be used.
For now, though, Pentland is excited about the potential of reality mining to simplify people's lives. "All of the devices that we have are completely ignorant of the things that matter most," he says. "They may know all sorts of stuff about Web pages and phone numbers. But at the end of the day, we live to interact with other people. Now, with reality mining, you can see how that happens ... it's an interesting God's-eye view."