Construction of a monitoring mode for online teaching based on big data

Direct transplantation of traditional classroom monitoring modes to online teaching scenarios leads to inherent incompatibility, as such modes fail to adapt to data-intensive nature of virtual instruction. Given the innate big data attributes of online teaching, big data technology emerges as an ideal solution to this problem. This study adopts an interpretive paradigm and qualitative approach with a thematic analysis design, using semi-structured in-depth interviews as the primary data generation instrument to explore the necessity, feasibility, and design of a big data-driven online teaching monitoring mode. Based on thematic analysis of interview data, a systematic monitoring mode is constructed, comprising four interconnected subsystems: a command system, an information collection system, an information analysis system, and an information feedback system. Distinct from prior research, this mode integrates multi-stakeholder practical insights with the analytical advantages of big data to develop a scalable online teaching monitoring framework, advancing the integration of technological innovation with educational quality assurance. This research provides theoretical and practical implications for promoting online teaching innovation and offers a novel methodological reference for online teaching monitoring practice.