Decoding sustainable entrepreneurship current research and future direction through application of machine learning-based structured topic modeling on intellectual corpus

Abstract This study leverages structured topic modeling (STM) to decode the expansive intellectual corpus on sustainable entrepreneurship, utilizing a dataset of 363 peer-reviewed articles from Scopus over a decade. Focused on “sustainable entrepreneurship” and related terms, the STM method integrated document-specific metadata to enhance the analysis of thematic developments. The findings revealed ten distinct topics, such as innovation in firm performance, sustainability in business models, and the role of education in sustainable intentions, highlighting the interplay between these themes and their evolution. This research identifies key thematic areas and examines the influence of source titles and publication years on topic prevalence, indicating shifts in academic focus and identifying emerging trends. The study’s implications suggest integrating sustainability into core business and educational strategies, enhancing the understanding of sustainable entrepreneurship’s dynamic nature, and providing a foundation for future scholarly and practical efforts.