Evaluation of the Model of College English Classroom Teaching Effect in the Digital Learning Environment

Abstract

Digital learning environments generate continuous streams of heterogeneous interaction data, creating increasing demands for efficient monitoring, information fusion, and adaptive evaluation. This study proposes a data-driven classroom effectiveness assessment framework by integrating the Plan– Do–Check–Act (PDCA) cycle with an ant colony optimization algorithm. A multidimensional evaluation architecture is established to characterize classroom vitality, organizational structure, and system resilience through teacher–student interaction data, learning-behavior records, and resource-utilization information. To improve evaluation reliability and optimization efficiency, the ant colony algorithm is employed to perform adaptive indicator-weight adjustment and evaluation-path optimization, while the PDCA mechanism provides a closed-loop feedback process for dynamic system refinement. Experimental results demonstrate that the proposed framework improves the efficiency of multi-source data integration, analysis, and feedback generation by approximately 16% compared with conventional evaluation approaches. Furthermore, the optimized model achieves higher consistency with teacher and student perceptions and exhibits enhanced adaptability in dynamic digital environments. The proposed framework provides an effective methodology for intelligent monitoring, multi-source information fusion, adaptive optimization, and data-driven decision support, offering potential references for networked sensing, information-processing, and intelligent evaluation systems.