Speaker
Description
Cross-border spatial identity refers to the multifaceted perceptions of identity that residents develop through their interactions and behaviors in cross-border spaces. It constitutes a critical framework for evaluating the progress of cross-border regional integration and plays an essential role in fostering a shared sense of regional community and advancing integration initiatives. The Shenzhen-Hong Kong region, as a key interface within the Guangdong-Hong Kong-Macao Greater Bay Area, faces distinctive challenges in cross-border integration due to the coexistence of diverse governance systems, institutional structures, and cultural frameworks within a single national context. These complexities necessitate an exploration of residents’ subjective identity with cross-border spaces from the perspective of their everyday spatial interactions. However, the inherent social, cultural, and linguistic diversity of cross-border spaces complicates such analyses, leading to challenges such as ambiguous measurement dimensions, difficulties in collecting long-term, high-quality data, and limitations in identifying and interpreting multidimensional emotional attributes. As a result, existing studies have yet to fully elucidate the dynamic evolution and heterogeneity of cross-border spatial identity.
To address these issues, this study develops an innovative measurement framework that integrates long-term, large-scale social media data with the advanced semantic analysis capabilities of large language models (LLMs). Using the Shenzhen-Hong Kong region as a case study, the research collects extensive social media textual data from platforms such as Weibo and Xiaohongshu, spanning the period from 2018 to 2023. Employing advanced semantic processing techniques, the study quantifies cross-border spatial identity across three distinct dimensions: spatial satisfaction, spatial imagery perception, and spatial belongingness. The findings reveal significant temporal fluctuations in the spatial identity of Hong Kong residents, particularly during pivotal events and policy milestones, including the COVID-19 pandemic and the promulgation of the Greater Bay Area Development Plan. Furthermore, the analysis highlights notable variations in cross-border spatial identity across different spatial typologies, with shopping and consumption spaces demonstrating especially positive identity perceptions. Importantly, substantial heterogeneity is observed in the spatial identity of residents from Shenzhen and Hong Kong, underscoring the influence of differing social, cultural, and spatial dynamics.
This study provides a robust, precise, and efficient methodological framework for the longitudinal measurement and analysis of cross-border spatial identity. By capturing the spatiotemporal dynamics and multidimensional heterogeneity of cross-border spatial identity, the research contributes critical theoretical insights and empirical evidence for the evaluation of regional integration processes. The findings offer practical implications for policymakers, enabling the design and optimization of strategies to enhance regional cohesion, foster a shared sense of community, and advance cross-border integration in complex sociopolitical contexts.
| Keywords | Cross-border Spatial Identity; Large language Models; Social Media Big Data; |
|---|---|
| Best Congress Paper Award | Yes |
