I always wondered if you could from the ground up visualize, delineate, and track ethnic neighborhoods in NYC without human input. All of the historic naturalization documents and ship manifests have been digitized and OCR'd now and include country of origin and nationality. By tracking the addresses from naturalization and census forms, a computer should be able to build a really accurate map of how neighborhoods changed and shifted from the 19th century through the early 20th up until the data becomes private.
For example, everyone in NYC knows that "Little Italy" is really a shadow of its former self and is mostly "Chinatown" now. If all the data was processed, you could visualize changes like that on a map over time and increase accuracy by adding more data sets (e.g. business directories, also in City archives).
For example, everyone in NYC knows that "Little Italy" is really a shadow of its former self and is mostly "Chinatown" now. If all the data was processed, you could visualize changes like that on a map over time and increase accuracy by adding more data sets (e.g. business directories, also in City archives).