Evaluation Method of Teaching Quality of Foreign Language Teachers in Colleges and Universities Based on Decision Tree Algorithm

Abstract

Abstract Teaching evaluation is an important part of the teaching process in colleges and universities and plays a very important role in the development of higher education and the improvement of education quality. Applying a decision tree algorithm to teaching evaluation can uncover the hidden intrinsic connection between teacher information and course quality evaluation results. This study combines the radar graph with the decision tree C4.5 algorithm to construct a foreign language teaching quality evaluation model, which explores the correlation between teacher information and radar graph attributes on teaching quality evaluation grades on the one hand and evaluates the predictive effect of the model on the other hand. The data mined by the radar chart-C4.5 evaluation model show that if the center of gravity of the radar chart is in the first quadrant, then the evaluation grade passes and has the highest support, which is 53.33%. If the radargram area is large, then the evaluation grade good has the highest confidence level of 77.27%. The evaluation result of the model is that the number of error samples of the prediction grade and the expert evaluation grade are 3 excellent, 5 good, 1 average, 4 qualified, and 1 poor, which proves that the performance of the radar map-C4.5 evaluation model is better.