Neighborhoods are vaguely defined, localized regions that share similar characteristics. They are most often defined, delineated, and named by the citizens that inhabit them rather than municipal government or commercial agencies. The names of these neighborhoods play an important role as a basis for community and sociodemographic identity, geographic communication, and historical context.
In our ongoing work we take a data-driven approach to identifying neighborhoods based on the geospatial properties of user-contributed data (e.g., rental listings, search queries, geotagged photos). Through a ensemble learning approaches we apply a set of spatial statistics for all n-grams in listing descriptions and demonstrate that neighborhood names and boundaries can be uniquely identified within urban settings.
