Felicia Chen (Computer Science, Statistics), Nikhil Pulimood (Computer Science, Mathematics), and James Wang (Statistics, Public Policy) spent ten weeks working with Counter Tools, a local nonprofit that provides support to over a dozen state health departments. The project goal was to understand how open source data can lead to the creation of a national database of tobacco retailers.
Project Results: The team performed a feasibility study involving questions of technical accuracy and cost-effectiveness. Working mostly in R, they used a combination of web-scraping for data collection, machine-learning and text mining for data classification, and MTurk for human validation, and were able to construct a viable dataset for North Carolina.
They presented findings at an informal briefing of civic leaders and planning officials.
Partially funded by Counter Tools
Click here for the Executive Summary
Project Lead & Project Manager: Mike Dolan Fliss, Counter Tools
“Coming in, I had little knowledge about what data science research entailed. Participating in Data+ was a great step and helped me better realize my career goals. I learned a host of interdisciplinary skills – ranging from web scraping to survey design – that can definitely be applied to future projects.” — Felicia Chen, Computer Science & Public Policy