Follow Datanami:
May 1, 2012

Researchers Turn Data into Dynamic Demographics

Datanami Staff

Aside from showing off how their travel, culinary and nightlife habits, users of the geolocated “check-in” service Foursquare could shed light on the character of a particular city and its neighborhoods.

Researchers at Carnegie Mellon University’s School of Computer Science say that instead of relying on stagnant, unyielding census and neighborhood zoning data to take the temperature of a given community, Foursquare checkin data can provide the much –needed layer of dynamic city life.

The researchers have developed developed an algorithm that takes the check-ins generated when foursquare members visit participating businesses or venues, and clusters them based on a combination of the location of the venues and the groups of people who most often visit them. This information is then mapped to reveal a city’s Livehoods, a term coined by the SCS researchers.

All of the Livehoods analysis is based on foursquare check-ins that users have shared publicly via social networks such as Twitter. This dataset of 18 million check-ins includes user ID, time, latitude and longitude, and the name and category of the venue for each check-in.

“Our goal is to understand how cities work through the lens of social media,” said Justin Cranshaw, a Ph.D. student in SCS’s Institute for Software Research.

The researchers analyzed data from foursquare, but the same computational techniques could be applied to several other databases of location information. The researchers are exploring applications to city planning, transportation and real estate development. Livehoods also could be useful for businesses developing marketing campaigns or for public health officials tracking the spread of disease.

For now, however, it’s being used to get a grip in the cultural and even class distinctions present in a community. For instance, in their study of Carnegie Mellon’s home in Pittsburgh, the researchers found that the Livehoods they identified sometimes spilled over existing neighborhood boundaries, or identified several communities within a neighborhood. The Pittsburgh analysis was based on 42,787 check-ins by 3,840 users at 5,349 venues.

For instance, “they found that the upscale neighborhood of Shadyside actually had two demographically distinct Livehoods — an older, staid community to the west and a younger, “indie” community to the east. Moreover, the younger Livehood spilled over into East Liberty, a neighborhood that long suffered from decay but recently has seen some upscale development.”

And how does this match up to the class and cultural viewpoints of a human observer? Right on… “That makes sense to me,” observed a 24-year-old resident of eastern Shadyside, one of 27 Pittsburgh residents who were interviewed by researchers to validate the findings. “I think at one point it was more walled off and this was poor (East Liberty) and this was wealthy (Shadyside) and now there are nice places in East Liberty and there’s some more diversity in this area (eastern Shadyside).”

Speaking of class divides, the limitations of the research shine through as a viable point of study themselves. Foursquare users tend to be young, urban professionals with smartphones. Consequently, areas of cities with older, poorer populations are nearly blank in the Livehoods maps—an indication of the class makeup—something potentially valuable when seeking new dwellings or pricing real estate, for instance.

Maps for New York (first map above), San Francisco (just above) and Pittsburgh are available on the project website, http://livehoods.org/.  The team has added voting for the next city to be “checked.”

Related Stories

Inside LinkedIn’s Expanding Data Universe

BI Giants Zoom in on Location Intelligence

JHU Sets Network Bar for Data-Intensive Science

 

Datanami