Teaching Quality Prediction of University English Courses Based on Machine Learning Technology

Abstract

Students’ academic progress and language proficiency are significantly shaped by the quality of instruction in English courses at the university level. English teaching quality prediction is the process of collecting, organizing, and analysing teaching status data in a thorough manner utilizing efficient technical methods in order to assign values and enhance teaching activities. In this manuscript, Teaching Quality Prediction of University English Courses using an Optimized Rotation-Invariant Coordinate Convolutional Neural Network (TQP-UEC-RICCNN-SBOA) is proposed. Initially domestic universities are the source of the input data. The input data is fed to pre-processing using Adaptive-Noise Augmented Kalman Filter (ANAKF) for the removal of incomplete and redundant data from the collected dataset. Then the RICCNN optimized with Secretary Bird Optimization Algorithm (SBOA) for accurate teaching quality prediction of English courses in the university. The proposed TQP-UEC-RICCNN-SBOA approach is implemented in Python and the performance metrics like Accuracy, Precision, Specificity, Recall, F1-Score, and ROC are analysed. The performance of the proposed TQP-UEC-RICCNN-SBOA approach attains18.25%, 22.5% and 30.7% higher accuracy, 17.35%, 24.9% and 31.50% higher Precision and 19.12%, 25.67% and 30.80% higher Recall compared with existing methods such as An Evaluation Approach for English Teaching Quality using DEA Fusion Algorithm(EA-ETQ-DEA-RBF), Online teaching quality evaluation model based on support vector machine and decision tree(OTQ-EM-SVM) and A Teaching Quality Evaluation Model for Preschool Teachers Based on Deep Learning(TQEM-PT-TS-ResNet) models respectively.