Leveraging natural language processing to bridge divides in sustainable transitions research

The growing need to address climate change through sustainability governance has amplified the importance of Sustainable Transitions Research (STR). Despite its interdisciplinary scope and methodological variety, STR continues to face divisions between research domains, often exacerbated by its rapid expansion and the methodological tensions between qualitative and quantitative approaches. This study uses natural language processing (NLP) to analyse 448 published articles, initiated from two foundational STR papers, to explore thematic and semantic patterns within the field. The NLP analysis reveals underlying connections and synergies across theoretical, empirical, and conceptual domains in STR, highlighting potential for cross-fertilisation between disparate research areas. The findings map key relationships across the STR community, providing a comprehensive overview of how different domains are interlinked. Recommendations include fostering hybrid approaches and enhancing collaboration between qualitative and quantitative research traditions. By bridging these divides, the STR field can advance in guiding more effective sustainability governance.