MIT’s Technology Review magazine has an interesting article on ‘reality mining’ – using mobile phone call and positioning data to build advanced models of social networks.
The article is part of their 2008 emerging technology series and looks at how data gathered from the mobile phone network can tell us about human behaviour.
The core technology is hardly new. The police have been generating social networks from phone records since the early to mid 90s in an attempt to solve cases.
What is new, however, is MIT’s Sandy Pentland has been using positioning data from mobile phones to look at how close people are to each other over time, to make the social networks much more accurate and information rich.
To create an accurate model of a person’s social network, for example, Pentland’s team combines a phone’s call logs with information about its proximity to other people’s devices, which is continuously collected by Bluetooth sensors. With the help of factor analysis, a statistical technique commonly used in the social sciences to explain correlations among multiple variables, the team identifies patterns in the data and translates them into maps of social relationships.
Such maps could be used, for instance, to accurately categorize the people in your address book as friends, family members, acquaintances, or coworkers. In turn, this information could be used to automatically establish privacy settings–for instance, allowing only your family to view your schedule. With location data added in, the phone could predict when you would be near someone in your network.
In a paper published last May [pdf], ¬≠Pentland and his group showed that cell-phone data enabled them to accurately model the social networks of about 100 MIT students and professors. They could also precisely predict where subjects would meet with members of their networks on any given day of the week.
This may strike you as equally terrifying and exciting. Obviously, it has huge potential for abuse by authorities, but the possibility of doing research on fully consenting participants who agree to be tracked for short periods for scientific research is huge.
There’s also a great short video where Pentland discusses the technology in a bit more detail, and mentions the possibility of using the data for informing how diseases spread through social networks,
While we’re on a social / mobile network tip, the New York Times has a fascinating article on the work of a Nokia anthropologist. He works largely in the developing world to try and understanding how phones are used and what effects they have on the social fabric and economic potential of the area.
Neuroanthropology also has a commentary on the article, pulling out some of the key social concepts it touches on.
Link to TechReview article on ‘reality mining’.
Link to video of Pentland discussing the technology.
pdf of full-text scientific paper.
Link to NYT article ‘Can the Cellphone Help End Global Poverty?’
Link to Neuroanthropology commentary.