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

<p>This paper combines the theory of multiple interactive teaching modes in the process of college English online teaching and constructs an interactive model of English online teaching from three dimensions: teacher-student interaction, student-student interaction, and human-computer interaction. Secondly, the learner portrait structure in the E-GPPE-C model was designed from the three dimensions of basic characteristics, behaviors, and outcomes. According to the planned group learning path, an improved convolutional neural network (CNN) is used to generate a personalized learning path. To divide the learning community, the group of learners is clustered using the mean clustering algorithm. Finally, three rounds of teaching practice were conducted to verify the effectiveness of this interactive teaching model. The results show that the ratio of verbal interaction between teachers and students after the use of the strategy of constructing learner profiles increased to 0.9 compared with the previous 0.1. The correlation coefficient between personalized learning and learning self-regulation is 0.682, and significant correlations all present a significant correlation at the 0.01 level. This paper provides lessons and references for further research and development of smart interactive instructional design in colleges and universities.</p>
</abstract>

This paper combines the theory of multiple interactive teaching modes in the process of college English online teaching and constructs an interactive model of English online teaching from three dimensions: teacher-student interaction, student-student interaction, and human-computer interaction. Secondly, the learner portrait structure in the E-GPPE-C model was designed from the three dimensions of basic characteristics, behaviors, and outcomes. According to the planned group learning path, an improved convolutional neural network (CNN) is used to generate a personalized learning path. To divide the learning community, the group of learners is clustered using the mean clustering algorithm. Finally, three rounds of teaching practice were conducted to verify the effectiveness of this interactive teaching model. The results show that the ratio of verbal interaction between teachers and students after the use of the strategy of constructing learner profiles increased to 0.9 compared with the previous 0.1. The correlation coefficient between personalized learning and learning self-regulation is 0.682, and significant correlations all present a significant correlation at the 0.01 level. This paper provides lessons and references for further research and development of smart interactive instructional design in colleges and universities.

An Online Interactive Model of University English Based on Comprehensive Evaluation Models

Applied Mathematics and Nonlinear Sciences

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

This paper combines the theory of multiple interactive teaching modes in the process of college English online teaching and constructs an interactive model of...

An Online Interactive Model of University English Based on Comprehensive Evaluation Models

Pubblicato online: 22 nov 2023

Pagine: -

Ricevuto: 19 feb 2023

Accettato: 02 giu 2023

DOI: https://doi.org/10.2478/amns.2023.2.01206

Parole chiave
Diverse and interactive teaching, Learner profiling, Convolutional neural networks, Personalized learning, Learning community

© 2023 Ying Zhou, published by Sciendo

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

An Online Interactive Model of University English Based on Comprehensive Evaluation Models

Pubblicato online: 22 nov 2023

Pagine: -

Ricevuto: 19 feb 2023

Accettato: 02 giu 2023

DOI: https://doi.org/10.2478/amns.2023.2.01206

Parole chiaveDiverse and interactive teaching, Learner profiling, Convolutional neural networks, Personalized learning, Learning community

© 2023 Ying Zhou, published by Sciendo

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

Parole chiave
Diverse and interactive teaching, Learner profiling, Convolutional neural networks, Personalized learning, Learning community