Coordinating Regional Governance and Urban-Rural Integration: Unraveling Regional Cooperation in Advancing Rural Development via NLP-Based Text Mining and Bayesian Best-Worst Model in Mega Metropolitan Regions, China

The sustainable development of rural areas is crucial for achieving regional balance in urbanized societies, particularly as cities and regions become increasingly interconnected. However, the role of regional cooperation in supporting rural revitalization and promoting sustainable urban-rural integration has been underexplored. This study addresses this gap by analyzing how coordinated efforts across multiple dimensions influence sustainable rural development within the Pearl River Delta, a key metropolitan region in China. A Rural Development Index (RDI) was developed to evaluate spatiotemporal dynamics by integrating rural social, environmental, and economic indicators. Leveraging geospatial data and regional policy records, we employed Bayesian best-worst methods to weight the sub-components of the RDI. The analysis used SnowNLP-based text mining and spatial network quantification to extract insights from regional cooperation affairs data. OLS and MGWR models were employed to reveal localized and aggregated cooperation impacts. Several key findings include: (1) Spatial disparities emerge, with regional cooperation affairs benefiting rural development concentrated in the core urban areas. (2) Economic cooperation is the major driver and leads the sustainable development, strengthening urban-rural linkages through strategic planning. (3) Environmental and social cooperation initiatives demonstrate the most consistent positive impacts, enhancing ecological sustainability, cultural vitality, and social services, whereas traditional rural investment models remain limited, underscoring the need for innovative and cross-sectoral planning tools. (4) Geographically, the positive effects of regional cooperation affairs peaked in 2016, followed by minor fluctuations. The findings offer actionable insights for data-driven policy frameworks, underscoring the importance of spatial intelligence in balancing rural and urban development.