Commercial Gentrification in the Platform Era: Differentiated Effects of Virtual and Physical Factors

Digital platforms are reshaping urban consumption spaces and altering the trajectory of commercial gentrification. However, research on how physical and virtual factors jointly shape commercial gentrification at the city scale remains limited. Taking the main urban area of Nanjing as a case, this study integrates platform and spatial data and applies machine learning methods to identify patterns of commercial gentrification and examine the roles of physical and virtual factors across different spatial types. The results show that: (1) typical commercial gentrification spaces in Nanjing exhibit a clear core-oriented pattern, concentrated in the traditional urban center and a limited number of emerging districts; (2) virtual factors become significantly more important as commercial gentrification intensifies, with online interaction intensity emerging as the most influential factor overall, while sentiment evaluation, influencer presence and proximity to platform hotspots play stronger roles in specific spatial types; and (3) physical and virtual factors have differentiated effects, combining in different ways to produce four distinct spatial patterns of commercial gentrification. This study reveals the differentiated roles of virtual and physical factors in shaping commercial gentrification at the city scale and enriches current understanding of urban commercial restructuring in the platform era.