The iconic Shikumen clusters in Shanghai represent key heritage sites facing significant challenges in sustainable urban regeneration. Balancing cultural preservation with tourism development has become a central focus for academic research. This study examines how various placemaking strategies interact to influence electronic word-of-mouth (eWOM) in these districts. Employing fuzzy-set qualitative comparative analysis (fsQCA), it analyzes the configurations of seven dimensions: greenery landscapes, quality amenities, heritage esthetics, destination image, cultural narratives, and integrated online-offline marketing. Data from web scraping, satellite image recognition, and surveys were collected across 20 Shikumen district cases. The findings reveal six distinct strategic configurations that drive either positive or negative eWOM outcomes. These results offer valuable theoretical insights and practical guidance for planning and managing urban heritage regeneration projects, contributing to a better understanding of the complex interplay between placemaking strategies and public perceptions in historic urban environments.

Generative Artificial Intelligence (GenAI)-assisted Virtual Reality (VR) heritage serious game design constitutes a complex adaptive socio-technical system in which natural language prompts act as control levers shaping designers’ cognition and action. However, the systemic effects of prompt type on agency construction, decision boundaries, and process strategy remain unclear. Treating the design setting as adaptive, we captured real-time interactions by collecting think-aloud data from 48 novice designers. Nine prompt categories were extracted and their cognitive effects were systematically analyzed through the Repertory Grid Technique (RGT), principal component analysis (PCA), and Ward clustering. These analyses revealed three perception profiles: tool-based, collaborative, and mentor-like. Strategy coding of 321 prompt-aligned utterances showed cluster-specific differences in path length, first moves, looping, and branching. Tool-based prompts reinforced boundary control through short linear refinements; collaborative prompts sustained moderate iterative enquiry cycles; mentor-like prompts triggered divergent exploration via self-loops and frequent jumps. We therefore propose a stage-adaptive framework that deploys mentor-like prompts for ideation, collaborative prompts for mid-phase iteration, and tool-based prompts for final verification. This approach balances creativity with procedural efficiency and offers a reusable blueprint for integrating prompt-driven agency modelling into GenAI design workflows.

Communities in China’s high-density cities, like Shanghai, are evolving from traditional residential roles into vibrant centers of entrepreneurial innovation. This research delves into the development of community-supported entrepreneurial ecosystems (CSEEs) in the city, with a specific focus on the sustainable co-creation mechanisms facilitated by stakeholders, explored through a comparative study framework. By utilizing Kelly’s Repertory Grid Technique, 14 essential elements of co-creation are identified, which form the framework for classifying the cases into three distinct types. This study employs in-depth interviews and content analysis to analyze and contrast how these co-creation patterns are applied across cases representing each type. The results show that key factors, such as resource origins, the interaction between CSEEs and embedded communities, and participant selection strategies, significantly shape the variations in value co-creation mechanisms, processes, and outcomes. Recognizing the variety of co-creation models is crucial for enhancing both the vitality and efficiency of Shanghai’s CSEEs. Furthermore, this study offers valuable insights into managing co-creation efforts and predicting risks in similar contexts, contributing to the sustainable regeneration of urban areas through community-driven entrepreneurship and innovation.