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

<p>In this paper, a Bayesian approach and a recommendation algorithm are used to construct a method for evaluating students’ competence in a hybrid teaching model. The Bayesian method is used to create a mathematical description of the student’s ability level. The purpose of classification is achieved by extracting features of students’ learning results and preference directions using the simple Bayesian method. According to the recommendation algorithm, the recommended objects’ content features are retrieved, and teaching resources with high matching degrees are recommended for students. The recommendation algorithm in this paper can effectively determine the ability level of students, as demonstrated by the results. The probability of the highest P1 mastery rate among A-E students is 0.3179 for B students, and the probability of the highest P2 mastery rate is 0.1409 for D students. The average score of the experimental class that implements blended teaching is 76.631, while the average score of the control class is 73.7841, and the experimental class is 2.8469 points higher than the control class. 2.8469 points. This study promotes the development and progress of blended teaching to a certain extent.</p>
</abstract>

In this paper, a Bayesian approach and a recommendation algorithm are used to construct a method for evaluating students’ competence in a hybrid teaching model. The Bayesian method is used to create a mathematical description of the student’s ability level. The purpose of classification is achieved by extracting features of students’ learning results and preference directions using the simple Bayesian method. According to the recommendation algorithm, the recommended objects’ content features are retrieved, and teaching resources with high matching degrees are recommended for students. The recommendation algorithm in this paper can effectively determine the ability level of students, as demonstrated by the results. The probability of the highest P1 mastery rate among A-E students is 0.3179 for B students, and the probability of the highest P2 mastery rate is 0.1409 for D students. The average score of the experimental class that implements blended teaching is 76.631, while the average score of the control class is 73.7841, and the experimental class is 2.8469 points higher than the control class. 2.8469 points. This study promotes the development and progress of blended teaching to a certain extent.

Exploration and Practice of Online-Offline Hybrid Teaching Mode in Teaching Higher Education Courses under the Background of Internet+

Applied Mathematics and Nonlinear Sciences

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

In this paper, a Bayesian approach and a recommendation algorithm are used to construct a method for evaluating students’ competence in a hybrid teaching...

Exploration and Practice of Online-Offline Hybrid Teaching Mode in Teaching Higher Education Courses under the Background of Internet+

Pubblicato online: 20 nov 2023

Pagine: -

Ricevuto: 25 feb 2023

Accettato: 31 mag 2023

DOI: https://doi.org/10.2478/amns.2023.2.01199

Parole chiave
Bayesian, Recommendation algorithm, Competency evaluation, Instructional resource allocation, Blended learning

© 2023 Yisha Wang et al., published by Sciendo

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

Exploration and Practice of Online-Offline Hybrid Teaching Mode in Teaching Higher Education Courses under the Background of Internet+

Pubblicato online: 20 nov 2023

Pagine: -

Ricevuto: 25 feb 2023

Accettato: 31 mag 2023

DOI: https://doi.org/10.2478/amns.2023.2.01199

Parole chiaveBayesian, Recommendation algorithm, Competency evaluation, Instructional resource allocation, Blended learning

© 2023 Yisha Wang et al., published by Sciendo

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

Parole chiave
Bayesian, Recommendation algorithm, Competency evaluation, Instructional resource allocation, Blended learning