Big Data-Driven Knowledge Management in English Vocabulary Teaching

Abstract

Against the “high input but low output” dilemma in traditional English vocabulary teaching and educational resource disparities, this study integrates big data analytics into vocabulary instruction to construct a data-driven knowledge management system encompassing multi-source data collection, instructional strategy optimization, and assessment reconstruction. A 16-week randomized controlled experiment (n=120) validated its efficacy: the experimental group showed significantly improved semantic network density, cross-domain association rate, and memory retention compared to the control group. Markov chain analysis revealed reduced error persistence (51.2% drop) and emergence of “advanced errors” (28.7%), indicating native-like language development. The study addresses gaps in educational big data and second-language vocabulary knowledge management, offering actionable strategies for enhancing vocabulary knowledge capture, transfer, and application in educational organizations—aligning with knowledge management principles of technical enablement and cognitive-organizational synergy.