Justin Cranshaw, Raz Schwartz, Jason Hong, and Norman Sadeh


International AAAI Conference on Weblogs and Social Media (ICWSM)


January 2012


Studying the social dynamics of a city on a large scale has traditionally been a challenging endeavor, often requiring long hours of observation and interviews, usually resulting in only a partial depiction of reality. To address this difficulty, we introduce a clustering model and research methodology for studying the structure and composition of a city on a large scale based on the social media its residents generate. We apply this new methodology to data from approximately 18 million check-ins collected from users of a location-based online social network. Unlike the boundaries of traditional municipal organizational units such as neighborhoods, which do not always reflect the character of life in these areas, our clusters, which we call __Livehoods__, are representations of the dynamic areas that comprise the city. We take a qualitative approach to validating these clusters, interviewing 27 residents of Pittsburgh, PA, to see how their perceptions of the city project onto our findings there. Our results provide strong support for the discovered clusters, showing how Livehoods reveal the distinctly characterized areas of the city and the forces that shape them.

Adobe acrobat reader