Typeface: Machine-Viewing Gentrification on Storefront Imagery in Bedford-Stuyvesant, Brooklyn

Gentrification—broadly, the replacement of a less powerful group by a more powerful one in an urban context—is oft-discussed in the popular press, but its definition is much-debated in the urban planning literature. Furthermore, academic treatments of displacement understandably focus on measurable yet fairly abstract indicators like changes in rent or income, whereas neighborhood change is often registered by residents on the ground using visual, but difficult-to-quantify markers like retail turnover. This project uses image recognition technology on a set of storefront photos to index the visual streetscape of a neighborhood, as well as to track changes to that portrait over time, and presents the findings in an accessible format on the web. The model relies on a binary classification developed by New York City cultural anthropologist Edward Snajdr and sociolinguist Shonna Trinch (2020), wherein colorful, text-heavy “old-school” storefront signage evokes openness, diversity and accessibility, while the spartan, symbolic and glass-laden “new-school” design signals clubbiness, cultural capital and upscale. The neighborhood focus is Bedford-Stuyvesant, a historically Black section of Brooklyn that has lately been in the top three community districts for proportional increases in rent, income, and white share of the population. The model finds a small but significant likelihood that old-school stores have closed, while more newly opened stores reflect the new-school style.