A legal technology project to automate analysis of district-specific regulations.
The Legal Constructs Lab has initiated a multi-phased legal technology project to facilitate collection and analysis of zoning information. This project aims to identify natural language processing techniques for automating information extraction from textual zoning codes. The outcome of this research will be better tools for understanding zoning, one of the most important, yet most understudied, governmental powers ordering our economy and society.
The first phase of this project involved a collaboration with researchers at the Urban Institute to test the effectiveness of a processing tool to read Connecticut zoning codes, using the “answers” of the standardized dataset created manually by the team behind the Connecticut Zoning Atlas. The resulting publication, "Automating Zoning Data Collection: Results from a Pilot Effort to Automate National Zoning Atlas Methodologies," has been published by the Urban Institute. The Lab's work on the project was funded by Open Philanthropy.
With that first phase completed, the Legal Constructs Lab is now collaborating with Professor Alexander Rush and his lab at Cornell Tech to extract structured data from a broader sample of codes from the National Zoning Atlas, with the goal of accuracy and attribution within the original codes. This second phase of work is funded by the National Science Foundation Human-Environment and Geographical Sciences Program and the Texas A&M AgriLife Extension Program.
The data infrastructure created by this project will facilitate concrete, actionable insights and unlock secondary research about zoning’s impact on housing availability, transportation systems, the environment, economic opportunity, educational opportunity, and our food supply.