With the development of online education, the evaluation method of teaching quality has also received wide attention. This paper took the "Comprehensive English" course on the Massive Open Online Courses (MOOC) platform as an example, established teaching quality evaluation indicators, designed an evaluation method based on a back-propagation neural network (BPNN), optimized the parameters of the BPNN by the improved genetic algorithm (GA), and established an improved GA-BPNN model. The results found that the error between the output of the improved GA-BPNN model and the actual value was the smallest, between 0.01 and 0.04, showing that the model was stable; the mean absolute percentage error (MAPE) and root-mean-square error (RMSE) of the improved GA-BPNN model were 0.051 and 4.778, respectively, which were superior to BPNN and GA-BPNN models. The results verify the reliability of the improved GA-BPNN model. The model can be applied in practical teaching.
展开▼