Leveraging augmented reality for historic streetscape regeneration decision-making: A big and small data approach with social media and stakeholder participation integration

Abstract

Urban regeneration through digital and intelligent technologies offers a critical solution to the challenges arising in rapid urbanization, such as resource misallocation, the revival of cultural heritage, and the pursuit of high-quality development. Despite its potential, this approach has been underexplored in current research. This research focuses on a historic streetscape to develop a framework integrating big and small data for Augmented Reality (AR)-driven regeneration decision-making. For big data analysis, SnowNLP was employed to conduct text mining analysis on spatial perception patterns extracted from user-generated content across social media platforms such as Weibo and Xiaohongshu. For small data, a comprehensive AR spatial demand questionnaire is developed to analyze visitors' and experts' opinions. By integrating big and small data into a GIS platform, a unified database is constructed, and the Ordinary Least Squares (OLS) regression models are applied to assess the correlations between physical space elements and social media factors about AR demands. The findings indicate that the proposed research framework is highly feasible, revealing significant correlations between physical and social media elements and AR demands. Specifically, physical elements such as Scenic Spots and Government Agencies demonstrate strong correlations with AR demands. Likewise, the positive sentiment expressed on Xiaohongshu strongly correlates with increased AR demands. Furthermore, it is expected that findings from this study will be able to inform the relevant planning policies and strategies in AR-driven urban regeneration, offering theoretical foundations and practical guidance for creating digital and sustainable urban landscapes.