<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The teaching of English courses in colleges and universities relies too much on grades to judge students’ mastery of knowledge points, and there are problems of slow feedback and difficulty in timely targeted teaching. To address the drawbacks of traditional English teaching methods, this paper constructs a random forest algorithm based on the decision tree model, uses the information gain index to judge the feature segmentation effect of the random forest, and calculates the degree of students’ mastery of knowledge points. At the same time, the recommendation model is utilized to match students with topics equivalent to their mastery level, and the alternating least squares method is introduced to improve its recommendation efficiency, thus constructing an efficient English teaching course assistance model. The model was implemented in colleges and universities after it had been designed. The highest similarity match of the educational resource ontology tree was achieved when the weights of knowledge points, resource difficulty, and resource type were 1.121, 0.986, and 1.129, respectively. The average score of the class was 65.3 before the application, after the application, the second test score increased to 69.28, which was a significant improvement, and the fourth test was 75.32, which exceeded the average score of 72.23. The investigation of this study shows the direction for the innovation of the English curriculum and promotes the benign development of English teaching.</p>
</abstract>

The teaching of English courses in colleges and universities relies too much on grades to judge students’ mastery of knowledge points, and there are problems of slow feedback and difficulty in timely targeted teaching. To address the drawbacks of traditional English teaching methods, this paper constructs a random forest algorithm based on the decision tree model, uses the information gain index to judge the feature segmentation effect of the random forest, and calculates the degree of students’ mastery of knowledge points. At the same time, the recommendation model is utilized to match students with topics equivalent to their mastery level, and the alternating least squares method is introduced to improve its recommendation efficiency, thus constructing an efficient English teaching course assistance model. The model was implemented in colleges and universities after it had been designed. The highest similarity match of the educational resource ontology tree was achieved when the weights of knowledge points, resource difficulty, and resource type were 1.121, 0.986, and 1.129, respectively. The average score of the class was 65.3 before the application, after the application, the second test score increased to 69.28, which was a significant improvement, and the fourth test was 75.32, which exceeded the average score of 72.23. The investigation of this study shows the direction for the innovation of the English curriculum and promotes the benign development of English teaching.

Exploring the Teaching Path of English Teaching Courses in Colleges and Universities Based on Decision Tree Modeling

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

The teaching of English courses in colleges and universities relies too much on grades to judge students’ mastery of knowledge points, and there are problems...

Exploring the Teaching Path of English Teaching Courses in Colleges and Universities Based on Decision Tree Modeling

Publié en ligne: 31 janv. 2024

Pages: -

Reçu: 20 déc. 2023

Accepté: 28 déc. 2023

DOI: https://doi.org/10.2478/amns-2024-0236

Mots clés
Decision tree model, Random forest, Recommendation model, Least squares, Information gain index, College English teaching

© 2024 Xuwei Jia, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Exploring the Teaching Path of English Teaching Courses in Colleges and Universities Based on Decision Tree Modeling

Publié en ligne: 31 janv. 2024

Pages: -

Reçu: 20 déc. 2023

Accepté: 28 déc. 2023

DOI: https://doi.org/10.2478/amns-2024-0236

Mots clésDecision tree model, Random forest, Recommendation model, Least squares, Information gain index, College English teaching

© 2024 Xuwei Jia, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
Decision tree model, Random forest, Recommendation model, Least squares, Information gain index, College English teaching