Article Preview
TopThe integration of IT and English courses impacted by the internet has been discussed by relevant scholars, and there are certain successes. Bozorgian and Alamdari (2018) pointed out that the role of IT is to help learners make research problems clearer, to make learners' inquiry behavior easier to occur, and to promote advanced thinking activities. Beer (2018) pointed out that, as the main participants of teaching, teachers' teaching level and ability assessment are particularly important, and the main method to evaluate instructional quality is the combination of supervision, peer teacher, and student assessment. Seedhouse and Supakorn (2015) pointed out that the current research on teaching level assessment mainly focuses on using traditional methods to fit and solve nonlinear problems, and the final results are affected by the bias of the researchers' subjective factors, which cannot accurately and effectively mine the non-linear problems in the assessment model. Park et al. (2016) mentioned that it is very common to focus on the results and ignore the process in the current teaching assessment. The usual method only pays attention to the students' assessment of the teacher's teaching results and does not lay emphasis on the teaching behavior in the instructional process. Nes et al. pointed out that the fuzzy comprehensive assessment model constructed by the AHP can remove the subjective component as much as possible by using the mathematical method with strict logic on the basis of expert knowledge and subjective experience, and reasonably determine the weight of the assessment index (El Soufi & See, 2019). In order to further improve the scientific basis and rationality of the quality evaluation of students' education management, Cao (2022) proposed a quality evaluation method of students' education management based on intuitive fuzzy information. Wu (2022) constructed the teaching evaluation system of vocational undergraduate pilot colleges and tested it, which also verifies that the construction of a teaching ability evaluation index system is reasonable and scientific. According to the research content of teaching performance evaluation, Xu et al. (2018) established the framework model of education data collection and storage platform on a smart campus. Teaching performance evaluation first analyzes the shortcomings of traditional evaluation methods, then uses PCA algorithm to determine six principal components, and uses AHP to calculate the weight of each layer of the index set to avoid decision errors caused by subjective factors. Finally, the TOPSIS algorithm is improved by using gray scale. The evaluation results of the AHP-TOPSIS teaching performance model are consistent with the actual situation. Qi et al. (2022) proposed an active learning algorithm, which combined a Gaussian mixture model and sparse Bayesian learning, and enhanced the SVM to select and label samples strategically to build a classifier and combine the distribution characteristics of samples. The results show that the proposed model is effective and beneficial in evaluating the efficiency of university teaching and analyzing large data sets. Wei and Cai (2022) studied the advantages and disadvantages of commonly used SVM parameter selection methods, such as a grid search algorithm, gradient descent algorithm, and swarm intelligence algorithm, and made a detailed analysis and comparison of other algorithms. Finally, the advantages and disadvantages of quantum particle swarm optimization (QPSO) are analyzed, and an improved QPSO is proposed by introducing a bicentric idea into QPSO. The simulation results show that the improved QPSO algorithm has more advantages in optimizing the parameters of the SVM.