Built Environment Equity and Area-Level Happiness: Distributional Imbalance and Spatial Discordance in Vulnerable Areas of Shanghai

Rapid urbanization has intensified inequalities in the built environment (BE), yet their relationship with well-being in areas where vulnerable populations are concentrated remains unclear. Using Shanghai as a case, this study examines the association between BE equity and area-level happiness across five types of vulnerable areas: those with larger numbers of minors, older adults, or migrant residents; economically disadvantaged areas; and areas with limited educational resources. We integrated geotagged Weibo check-in texts collected from January to December 2023, multi-source spatial data, street-view imagery, and interpretable machine learning. ERNIE 3.0 was used to derive sentiment scores from individual posts, which were then aggregated within each spatial unit to construct an area-level happiness score. Thirty-four BE indicators were organized within the 5D framework and analyzed using Mask2Former, Moran’s I, Gini coefficients, LightGBM, and SHAP. Results reveal marked central–peripheral disparities in BE resources and happiness, together with nonlinear and group-specific spatial associations. High-Gini patterns are evident in peri-urban areas, accounting for approximately 67% of vulnerability-focused areas, while strict equity–happiness discordance accounts for 42%. These findings suggest that BE distributional imbalance, adverse high-inequality–low-happiness co-occurrence, and equity–happiness discordance should be distinguished for targeted and inclusive planning.