Marshall Kirkpatrick over at ReadWriteWeb shares, with some optimism and a lot of caution, the Reality Mining project, being conducted by the Human Dynamics Group at the MIT Media Lab. They are processing more than 350,000 hours of data collected from peoples' cell phones. More than just who calls who, Pentland is also studying proximity, location and activity data using information like interactions recorded between Bluetooth devices. [images in this post from the Reality Mining website]

More details on the project at Nicholas Carr's blog:

In a paper entitled "Inferring Social Network Structure Using Mobile Phone Data," Pentland and two coauthors explain that one of the great benefits of the cell phone as a data mining tool is that it provides raw, unfiltered information, which ends up being more reliable than information "self-reported" by people. People's reports on their own behavior are subject to a great deal of distortion due to memory lapses, cognitive biases, embarrassment, and other factors. Cell-phone reality mining, by contrast, provides "a new method for precise measurements of large-scale human behavior." Our cell phone know us better than we know ourselves.

To illustrate the power of the technique, the authors conducted a reality mining experiment that involved "ninety-four subjects using mobile phones pre-installed with several pieces of software that record and send the researcher data on call logs, Bluetooth devices in proximity, cell tower IDs, application usage, and phone status. These subjects were observed via mobile phones over the course of nine months, representing over 330,000 person-hours of data (about 35 years worth of observations)." The data provided a remarkably intimate view of the subjects' lives. The researchers were, for instance, able to "identify characteristic behavioral signatures of relationships that allowed us to accurately predict 95% of the reciprocated friendships in the study. Using these behavioral signatures we can predict, in turn, individual-level outcomes such as job satisfaction."

In an interview with Kate Greene of Technology Review, Professor Alex (Sandy) Pentland, the senior faculty on this project, claims that reality mining can help solve social problems, big and small:

TR: What could be some benefits to all this measurement?

SP: You can really see things in a way that you never could before-a God's-eye view. One of the examples I've been stuck on recently relates to how transformative Google Earth has been. Imagine having something where you can see all the people moving around on a map. Think about SARS in Hong Kong. What if in a particular apartment building, nobody left for work that day? You could identify a major health problem in 12 hours instead of two weeks. Another example is the social health of communities. It's known that social integration, or how well people mix, correlates with whether or not a community is thriving. With reality mining, you can actually see social integration, as it happens or doesn't happen. Once everyone can see it, then you can start to have transparent political discussions. Why isn't the mayor putting more sidewalks and crosswalks in this area? Could more community events make the area more livable?

I'm not so sure how this will work.

As a researcher working in a commercial marketplace, however, my eyes light up at the potential mining and processing this data would have in several areas: segmentation and user-behaviour modelling and prediction studies on all sorts of parameters based on an observation of actual behaviour- demographic, contextual and social interaction, motivational, community, relational, efficiency, mapping - the possibilities are endless when you have such masses of 'real' raw data. With many commercial implications and potential - to feed into explorations and fine-tuning of market positioning opportunities, UI and design experiments, social networking and community building (which may or maynot be exploited commercially), mobile marketing and value-added services.

But, as a user of a mobile phone, I am quite worried by it. I want to control my information, and I want to be able to decide who has access to it. I don't want my mobile phone to reveal more of me, than I want it to. I want less intrusions, interruptions and invasions - they're one of my biggest cribs already - I fear that there will only be more. I want an opt-in/opt-out option for sure.
Surveillance or research? Invasive or transformative? Benefit to community or commerce?

Lets see what shape this takes!

Share This