A Behavior Sequence Based Psychological Feature Extraction Model for Students in English Teaching

Abstract

With the rapid development of science and technology, intelligent teaching has been gradually popularized in the campus, and the change of relevant teaching modes has also been carried out. In the new English teaching, it is necessary to analyze the students’ psychological behavior. In order to get accurate results, the research captures the students’ behavior as a behavior sequence, and uses the improved combined kernel support vector machine to extract features on the basis of approximate entropy and local mean decomposition. At the same time, it is compared with the traditional support vector machine, the traditional least square vector machine and the back-propagation neural network algorithm. The experimental results show that the improved algorithm has higher accuracy, recall and accuracy than the other three algorithms. The overall accuracy of the improved algorithm is 82.53%, the highest accuracy is 90.12%, the overall recall is 58.64% and the overall precision is 86.92%. The experimental results show that the improved algorithm has a significant improvement in performance, and can be applied to the extraction of students’ psychological characteristics. Therefore, the algorithm can be used in conventional blended English teaching, which is convenient for teachers to carry out English teaching more efficiently.