Who gets quality urban parks? A socioeconomic disparity analysis using user reviews and the opportunity algorithm in Los Angeles

Abstract

This study explores urban park equity by leveraging user-generated content from Google Maps and applying the opportunity algorithm to assess disparities in park quality. We investigated whether perceived needs and satisfaction levels related to park features vary by neighborhood income level, racial composition, and park size. The opportunity algorithm identifies underserved and overserved features by comparing the relative importance and satisfaction scores. The results revealed that different park groups exhibited distinct underserved and overserved features. Safety concerns are underserved in low-income and minority neighborhoods. Conversely, amenities such as hiking and biking or natural features are often overserved in high-income or high-white areas. Furthermore, dog parks were viewed as overserved in low-white areas but underserved in high-white areas, reflecting a reversed pattern. These findings demonstrate the effectiveness of the opportunity algorithm approach in detecting user perceptions of park quality by identifying mismatches between importance and satisfaction, offering a scalable, data-driven alternative to traditional audits. Based on these insights, we propose policy recommendations to support more inclusive and responsive urban park planning.