Mapping Knowledge Reconfiguration in E-Commerce Research: A Reproducible Semantic-Temporal Framework Integrating BERTopic and Event-Based Inference

This study investigates the temporal evolution of e-commerce research topics from 1996 to 2025 using a reproducible semantic–temporal framework that combines a fixed-seed K = 20 BERTopic specification with adjacent-year Pearson correlation coefficient (PCC) linkage and inheritance–differentiation–convergence–emergence–extinction (IDCEX) event inference. The eight-category Web of Science main corpus contains 13,078 documents. The analysis identifies 20 interpretable topics and 476 evolutionary events: 11 inheritance, 276 differentiation, 155 convergence, 20 emergence, and 14 extinction events. The strongest turning interval is 2012–2013, followed by 2000–2001 and 2011–2012. A rank-1 backbone trajectory spans 1998–2025 and shifts from intelligent and fuzzy multi-agent decision support (T8) to small and medium-sized enterprise (SME) digital transformation, business-to-business (B2B) activity, and supply-chain ecosystems (T0) in 2012. These findings characterize e-commerce knowledge development as a combination of specialization, recombination, and selective long-run continuity.