Traditional expert–driven technology foresight is often limited by subjectivity, low replicability, and high costs. To address these challenges, this study proposes a novel, data–driven framework for technology foresight that offers an objective, scalable, and multi–dimensional approach to identifying and prioritizing emerging technologies in the railway industry. Our tripartite methodology systematically integrates three analytical dimensions: (1) Temporal Forecasting using Autoregressive Integrated Moving Average (ARIMA) models to project the growth trajectories of technology keywords; (2) Structural Analysis using Social Network Analysis (SNA) to evaluate the systemic importance and influence of technologies within the innovation network; and (3) Semantic Analysis using BERT–based contextual embeddings to track the longitudinal evolution of technological concepts. By applying this framework to 4,199 patents from the Korean Intellectual Property Office (1990–2023), we demonstrate its efficacy. The results identify a portfolio of high–priority technologies, such as “sensor,” “signal,” and “control,” which exhibit both strong growth momentum and high network centrality. Critically, our semantic drift analysis reveals a significant paradigm shift, exemplified by the term “device,” which has evolved from representing simple mechanical components to denoting complex digital control systems. This integrated framework provides a robust, transparent, and replicable methodology for strategic technology roadmapping, offering actionable intelligence that moves beyond static analysis to capture the dynamic nature of technological evolution.
Lee et al. (Sat,) studied this question.