Sign In

Communications of the ACM

ACM TechNews

Unequal Park Quality Exposed Using Social Media, Machine Learning

View as: Print Mobile App Share:
People enjoying Philadelphia's Fairmount Park.

The study found that a majority of Philadelphia's urban parks that are considered to be of high quality are located in areas that tend to have more affluent, white, and college-educated residents.

Credit: R. Kennedy/Visit Philadelphia

Researchers at the University of Delaware (UD) and Emory University exposed unequal quality in Philadelphia's urban parks using social media and machine learning (ML).

The researchers used an algorithm to analyze 285 parks using more than 100,000 reviews collated from Google Maps, showing most high-quality-designated parks are sited in areas where affluent, white, college-educated residents are prevalent.

The lowest-scoring parks tended to be in neighborhoods inhabited by historically marginalized citizenry, mainly low-income, less-educated Black and Hispanic residents.

UD's Matthew Walter said the researchers used natural language processing to condense the reviews' text into different categories or topics to see the most frequently mentioned keywords.

The researchers also used satellite and aerial imagery and data from police reports and the Philadelphia Parks and Recreation Department to corroborate the reviews with the parks' physical properties.

From UDaily
View Full Article


Abstracts Copyright © 2023 SmithBucklin, Washington, D.C., USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account