Unveiling the Triple Transformation in Supply Chain Management: A BERT-Based Topic Modeling and Fuzzy C-Means Clustering Approach

The altering dynamics of supply chain management are increasingly influenced by the progressive adaptation of digital, green, and social transformations, named under the "triple transformation". This study aims to thoroughly examine the existing academic literature regarding the triple transformation in supply chains through the application of modern natural language processing and clustering methodologies. A corpus of 5586, 5575, and 7672 peer-reviewed articles is obtained for social, digital, and green transformation respectively. Bidirectional Encoder Representation from Transformers (BERT)-based topic modeling is used to reveal underlying theme structures, facilitating semantically rich embedding and contextualized topic extraction. Subsequently, the identified topics are categorized utilizing the fuzzy c-means clustering technique to examine the intersections and differences across research themes pertaining to digitalization, sustainability, and social responsibility in supply chains. The results provide a detailed overview of the research gap, emphasizing fundamental topics, interdisciplinary trends, and upcoming issues.