Key points are not available for this paper at this time.
In the context of informatization, online teaching is increasingly favored by people for its convenience and resource richness. Through the Open CourseWar (MOOC) platform, people can easily access learning resources and achieve efficient line length learning. However, currently MOOC online learning cannot provide targeted evaluation for the learning effectiveness of English learners, and there is relatively little research on online English quality assessment. Propose an intelligent MOOC online English teaching evaluation technology. Firstly, analyze the existing English teaching factors and construct a quality evaluation system for online English teaching using Principal Component Analysis (PCA) and expert evaluation method. Considering that the quality of English teaching is influenced by many factors, the evaluation of English teaching quality belongs to a complex nonlinear solving problem. Therefore, the advanced GA-RBF (Genetic Algorithm Radial Basis Function Neural Network, GA-RBF) model is adopted to solve the English teaching quality evaluation model. In teaching quality evaluation, BP and RBF are selected to participate in comparative testing of teaching quality evaluation. In the training loss test of multiple models, the GA-RBF model has the best convergence speed and training performance in the oral sample test, tends to converge after 270 iterations, with a loss value of 0.24. In the evaluation of English proficiency indicators, the BP model has a significant error in testing, with an error of 13 in the evaluation of reading ability scores. The error of RBF in reading ability score evaluation is 4, and the GA-RBF model performs the best. The reading ability evaluation error is 1, and the overall evaluation performance is the best. Through the above research, an intelligent method for evaluating the quality of English teaching is proposed, which will provide important technical references for MOOC online education evaluation and English teaching improvement.
Qin Xiao (Sun,) studied this question.