Land transition in China has led to the emergence of highly heterogeneous neighborhoods. This process challenges the social sustainability of public green spaces. This research investigates the driving mechanisms of place attachment within green space across diverse community typologies in Beijing. This study constructed a structural equation model (SEM) based on 626 valid questionnaires, using the Stimulus–Organism–Response (S-O-R) framework. The overall SEM results indicate that place identity significantly contributes to civic behavior (β = 0.439, p < 0.001). However, a persistent ‘value-action’ gap remains, with 65.81% of residents demonstrating high identity yet low participation. Furthermore, the multi-group analysis (MGA) reveals that place attachment logic diverges significantly across groups. Regarding user identity, public events promote visitors’ place identity, but this effect remains insignificant among residents (β = −0.064, p > 0.05). Regarding generational differences, the macro-spatial environment is significantly associated with place dependence for young people (β = 0.330, p < 0.001) but is insignificant for the elderly. Community heterogeneity reveals distinct failure modes. In commodity housing communities, a disconnect exists where daily usage fails to foster dependence (β = 0.026, p > 0.05). Conversely, urban–rural resettlement communities display an identity deficit where public events fail to translate into place identity (β = 0.131, p > 0.05). The study proposes differentiated renewal pathways tailored to three community types. For commercial housing communities, it advocates precise interventions that prioritize social engagement. Meanwhile, for urban–rural resettlement communities, the focus shifts to accessibility and culturally rooted activities to help reconnect displaced populations.

This study investigates the nonlinear, interactive, and temporally dynamic effects of urban form on street vitality within community-oriented metro station areas (MSAs) in Beijing. It offers potential reference value for other cities facing comparable challenges in MSA implementation and increasing motorization. This research addresses gaps in prior studies concerning the integration of multi-source data, nonlinearity, and diurnal variation. Utilizing an extended node-place-design framework, urban form is conceptualized through network, interface, and functional dimensions. The empirical analysis employs multi-source datasets, including 128,199 mobile device trips recorded in April 2024, OpenStreetMap for network data, Baidu points of interest for functional data, and Grasshopper for interface metrics, covering 183 street samples within a 1000 m radius of metro stations. Traditional regression models—such as ordinary least squares and spatial autocorrelation and cross-correlation—are used as baselines, while a novel gradient-boosting decision tree with latitude and longitude features is applied to enhance predictive performance. The results indicate that key contributors include road network density (16.89%), road intersections (10.56%), and point-of-interest density (9.74%), with Shapley Additive Explanations dependence plots demonstrating nonlinear thresholds. The analyses reveal synergistic or antagonistic interactions among features. Temporal fluctuations in feature importance further support the presence of diurnal dynamics. The study provides insights for time-sensitive urban planning aimed at enhancing MSA vitality, sustainability, and resident quality of life, while acknowledging that the conclusions are context-specific to Beijing and require additional validation in other urban environments.