Teaching Effect Evaluation System of Ideological and Political Teaching Based on Supervised Learning

Abstract

University students face immense challenges in current situations in ideological and political research. Therefore, the way ideological work constantly needs to be adapted, and the exchange of advanced experience strengthened to increase ideological and political education (IPE) in universities. Specific methods of university administration may include only ideological and political courses. Courses information and student grades did not conduct an ideological or political evaluation of the student. They assessed the psychological behaviors of the student based on their success, nor did them include clear information on the course schedule for specific ideological and political courses. This article, Supervised learning-based teaching evaluation approach (SL-TEA), has been proposed to focus on supervised learning from ideas about machine learning technology and the current IPE status, to be developed using a brief analysis procedure. Supervised learning uses a practice set to provide the necessary quality through teaching models. Inputs and correct outputs that allow the model to learn over time are part of this training data. The study uses the system of experts to manage, operate and monitor model evaluation data and create a related database for a real-time update. Besides, to check the impact of the model and to run simulation tests. This study SL-TEA model follows the real needs of the system that the ideological and political teaching content of colleges and colleges can be evaluated. Thus, the experimental results show the better performance through the highest student accuracy ratio of 97.1 %, a high-performance ratio of 94.3%, improved political thinking rate of 92.8%, improved actual positive rate of 90.2%, the false-positive rate of 92.2%, enhance learning rate of 96.6% and reduce the error rate 21.2%, compared to other methods.