SC Faculty and Researchers
The Livehoods Project presents a new methodology for studying the dynamics, structure, and character of a city on a large scale using social media and machine learning. Using data such as tweets and check-ins, we are able to discover the hidden structures of the city with machine learning. Our techniques reveal a snap-shot of the dynamic areas that comprise the city, which we call Livehoods.
Livehoods allow us to investigate and explore how people actually use the city, simultaneosly shedding light onto the factors that come together to shape the urban landscape and the social texture of city life, including municipal borders, demographics, economic development, resources, geography, and planning.
The hypothesis underlying our work is that the character of an urban area is defined not just by the the types of places found there, but also by the people who make the area part of their daily routine. To explore this hypothesis, given data from over 18 million foursquare check-ins, we introduce a model that groups nearby venues into areas based on patterns in the set of people who check-in to them. By examining patterns in these check-ins, we can learn about the different areas that comprise the city, allowing us to study the social dynamics, structure, and character of cities on a large scale.
Results and Applications
We call the resulting areas Livehoods, reflecting the dynamic nature of activity patterns in the lives of city inhabitants. Like neighborhoods, Livehoods are a representation of the organizational structure of the city. However, Livehoods are different from neighborhoods. They give us an on-the-ground view of a city's structure, helping us reconceptualize the dynamics of a city based on the way people actually use it.
With Livehoods, we can investigate and explore the factors that come together to shape the social dynamics of a city, including municipal borders, demographics, economic development, resources, geography, and architecture. We think Livehoods are useful for city governments, local organizations, businesses, and anyone looking to learn more about a city. If you have an idea of how Livehoods might be helpful to you or your city, tell us about it.
We are proud to be working with the following faculty and researchers from across Carnegie Mellon and the world:
Justin Cranshaw (Microsoft Research)
Jason Hong (CMU HCII)
Raz Schwartz (Facebook Research)