Identifying Park Inequities Through Data Science

According to a new study from the University of Delaware, park access and quality vary across the city of Philadelphia. Using a machine learning algorithm to analyze 285 parks from over 100,000 park reviews gathered from Google Maps, the study shows that a majority of the parks that are considered to be of high quality are located in areas that are more likely have more affluent, white, and college educated residents. The parks that scored the lowest tend to be in areas where the residents are historically marginalized, including mostly low-income, Black and Latino, with a lower level of educational attainment.

As reported by Adam Thomas, the researchers corroborated the reviews with the physical characteristics of those parks using satellite and aerial imagery, as well as police reports and data from the Philadelphia Parks and Recreation Department. The study was published in Scientific Reports and was led by Matthew Walter, a doctoral student at the University of Delaware. Walter shared that by reading social media reviews of parks from 2011 to 2022 and by examining a large amount of reviews spread across a wide range of parks, he and his fellow researchers were able to see how a large population of Philadelphia was feeling about its urban parks.

Of particular concern to the researchers was that one key demographic group that lacked access to highly rated parks were the ones who needed them the most: young children. In the areas where the census data showed more young children, the park reviews were more likely to mention condition and safety when compared to other topics. This lower perceived park quality for young children raises a concern for childhood health and development.