In the practical application of MOOC English teaching quality evaluation, the entropy method exhibits high sensitivity to the degree of data dispersion. Once the sample data presents a local concentration trend or is disturbed by extreme values, it will cause an imbalance in the allocation of indicator weights, ultimately undermining the evaluation accuracy. Therefore, a research on fuzzy comprehensive evaluation of MOOC English teaching quality based on improved entropy method is proposed. In this method, an evaluation index system is constructed for MOOC English teaching quality, and grey relational analysis is conducted to screen indicators. Then indicator data is collected, and outlier cleaning is performed to ensure data quality. Subsequently, with processed indicator data as input, the entropy method is used to determine indicator weights, and fuzzy comprehensive evaluation method is applied to improve indicator weights. Based on the determined indicator weights, the fuzzy comprehensive evaluation of MOOC English teaching quality is completed. The results show that this method can effectively determine key evaluation indicators, with a high sensitivity coefficient of 1.97, the highest evaluation accuracy of 0.98, and the highest evaluation time of 3.792 seconds, demonstrating a good evaluation performance.
Yifan Liang (Thu,) studied this question.