Structural equation modeling (SEM) studies commonly derive constructs and paths from the manually reviewed literature. Expert judgment remains essential, but incomplete coverage and undocumented selection decisions can make this stage difficult to evaluate. We therefore develop a theory-guided, AI-assisted procedure for generating SEM candidate models from systematic literature evidence. PICOC defines the scope, and queries identify the primary records. Backward citation searching adds foundational studies, whereas forward searching adds recent applications. Sentence-BERT and BERTopic are then used to examine semantic structure. Topic terms, representative documents, concept evidence, and theoretical criteria inform the mapping from topics to candidate constructs. The retained constructs are assigned possible SEM roles and assembled into candidate paths. The result is a documented front-end method for candidate model development, not an empirically validated SEM model.
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.