A Map Of Your City’s Invisible Neighborhoods, According To Foursquare

Using algorithms, a team of students analyzed the clusters of places that like-minded people flock to.

Every city is filled with different neighborhoods, but often, you won’t find these places on any map. They’re word-of-mouth zoning distinctions known only to locals. The boundaries are vague and arbitrary, based as much upon the way people eat and dress as real estate prices and income per capita.

Yet if these areas are distinctive to city culture, is there a way that we could measure them and analyze them—map them—scientifically?

A team of students (Justin Cranshaw, Raz Schwartz) and professors (Jason I. Hong and Norman Sadeh) from Carnegie Mellon’s Mobile Commerce Lab has done just that. Their research project is called Livehoods, which analyzed 18 million Foursquare check-ins to spot algorithmic relationships between the spots people frequent. “Livehoods looks at the geographic distance between venues, but also a form of ‘social distance’ that measures the degree of overlap in the people that check-in to them,” the team tells Co.Design. “For example, if the algorithm notices that the people that visit a local bar are the same people that visit a nearby restaurant, these two places will be more likely to be grouped together.”

As more and more people and places are analyzed, Livehoods clusters this data into what becomes a collection distinctive neighborhoods—places filled with people who enjoy going to the same restaurants, coffee shops, and music venues. And as calculating as the approach could seem, Livehoods’ scientific basis makes it extremely valuable as a social artifact: It defines local culture without the inherent judgement that comes along with human stereotyping.

With this scientific methodology in mind, the Livehoods team cross-checked their own findings of Pittsburgh with 27 resident interviews. What they found—the full results which will be shared in a paper presented this June—was “compelling evidence” neighborhoods as Livehood algorithms had defined them had “real social meaning to people in the city.” In other words, the digital map lined up with many residents’ own mental maps.

All of this said, Livehoods aren’t a perfect snapshot of humanity just yet. The datasets mined for the project are limited by the perspective of Foursquare users. A lot of us don’t use Foursquare (with a strong skew toward older adults, most likely). “Our technique, however, is agnostic to the specific source of the data,” the team explains, “so as we get better, less biased sources of data, we should be able to produce more accurate views of the city.”

The young researchers also fear that we may take their boundaries a bit too literally. As much as Livehoods works to clarify invisible distinctions, the team, paradoxically, points out that these distinctions are more subtle than we might expect.

“In reality, neighborhoods tend to blend into one another,” they write. In which case, may I suggest a simple UI tweak? Maybe Livehoods should be rendered in gradients.

[Hat tip: Creative Applications]

Add New Comment

12 Comments

  • lamyaimpala

    For many part of the world like countries in africa, many of the cities and towns dont have clear outlining, and neighborhoods are not defined at all. website should support allowing residents of neighborhood to plot their boundary of their neighborhood and city. I think it will also help develop the services sector, as many service providers depend on attending the client at their home address, or deliver things to them. www.innwan.com is an example of a website in africa that is helping users to map their address and develop a resident view of the neighborhood and city boundaries. I think we will see many more website help solve mapping and naming streets by how locals name them if there is no public department that develops an address system for them.

  • Haronniin

    Something like this could be useful even for small and/or rural communities.  Having recently relocated to rural Nebraska, I discovered there are numerous "hot spots" around that exist largely by word of mouth - and as I gain foursquare friends from the area I discover their checkins at these locals.  I'm sure there are many more locations I've not yet discovered which might be more readily found with such a map. It would also be a handy set of data to add to my ethnography of the area (I do mix business and pleasure). 

  • Steven Leighton

     When I moved to live in Manhattan I was offered a very low rent studio as part of the incentive package or an allowance to help pay for somewhere else. When I looked on a paper map (1985) the studio looked to be slapbang in the middle of everything. It was on 43rd st between 5th and 6th(!).
    Actually it was a social dead zone with a fire station as a neighbor (full siren and lights call outs all night long).
    A data map like this would have helped me access info from North Carolina about where to live to enjoy the Boro more.
    Also If I wanted to open a retail or restaurant or service business this could prove very helpful.
    Good idea, not great, needs more data input.

  • AnonDesignCollective

    While some of the Livehood densities shown simply confirm unspoken understandings of where various "types" of people frequent....the potentially more interesting story is the lack of density in various areas....and why?

  • FS

    This is very informative. Just looking at very downtown NYC, it's fascinating and telling of certain neighborhood populations... I find it interesting how the red Downtowners don't cross over into South Street Seaport mall, and how the mall is actually filled with people from Brooklyn. Knowing it's all Foursquare, it's kind of cool to see how people entertain and/or supply themselves at nearby hubs, and which hubs people gravitate towards.

    Pfft 

  • Railingk

    So.... four scientists crunched a lot of data to determine that people in Williamsburg check in from a lot of places in Williamsburg, people in Chelsea check in from a lot of places in Chelsea.... and sometimes they check in from adjacent neighborhoods. Every single New Yorker could have told you where these neighborhood demarcations are without consulting a dataset.

    This really is not impressive.

  • Barbionit

    It is really clear to me that this kind of mapping exposes the hidden differences and assumptions in our stereotyping, those that separate the check ins into the different areas. In a precise way, different from those "any New Yorker could have told you" we see  how our hidden assumptions about human behavior separate us into different economic behaviors.
       In one neighborhood, let's say, all people are tolerant to gays.  But at one end of the neighborhood  stores  are selling goods like sushi, massages  and at the other there are hamburger joints and bridal parlors, and rental agencies. Some gays eat meat, some don't.  We don't always see the differences.

  • Igor Pismensky

    Facebook seems to be acquiring data from its subscribers (those who do this) when they check in or tag a person as being checked in at locations they frequent. 
     

  • ElTronBomb

    Aren't there cultural issues here? I mean, it seems like the researchers might want to consider a host of other socio-economic indicators aside from age that would be influencing the use of four square. 

  • Sunanda Nair

    Agree. I think this idea is very interesting but how is socio-economic status of the people living in certain neighborhoods affecting these results. Also foursquare does little to stop false checkins. Maybe add something other than foursquare checkins as a next step.