Indonesia’s capital relocation to Nusantara poses societal, economic, and environmental challenges. This bibliometric study analyzes 132 Scopus publications (2019–2024) to explore machine learning (ML) applications in social network analysis (SNA) for understanding public sentiment and infrastructure impacts. Using VOSviewer, results highlight the prominence of sentiment analysis via platforms like Twitter, with support vector machines (SVMs) commonly applied to assess environmental and land-use concerns. However, gaps exist in platform diversity, longitudinal sentiment tracking, and integrated spatial-social analytics. Practical recommendations include real-time sentiment dashboards, GIS-based environmental monitoring, and multi-platform social media analysis to support sustainable urban development. Future research should integrate sentiment analysis with geographic information systems (GIS), demographic data, and environmental metrics for holistic policy insights.
Keywords: Indonesia, machine learning, relocation, social network analysis