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

<p>In the globalization of big data, how to use big data technology to evaluate the text of college English teaching materials and design the interactive system is a hot issue of current concern. In this paper, firstly, we design the interactive system of university English teaching based on the middle dense vector, knowledge embedding vector, learning feature vector, and other letter cores of fused interactive information, implement the interactive interaction system and debug it. Then the index system is constructed based on the evaluation data of English majors and students in a Normal University on university English teaching materials. Finally, the university English teaching materials evaluation grade data analysis uses a multilayer perceptron neural network. The results showed that the accuracy rate of nine indicators was 73.56%~80.36% for excellent evaluation grade, 86.23%~88.53% for good evaluation grade, and 63.96%~69.43% for average evaluation grade. The accuracy rate of good evaluation grades is higher than the other two categories. This study comprehensively and accurately analyzes the text evaluation of college English textbooks by English majors and students in central China; this university to improve the applicability and group of college English textbooks in a targeted way and promote the improvement of the teaching quality of college English courses in universities.</p>
</abstract>

In the globalization of big data, how to use big data technology to evaluate the text of college English teaching materials and design the interactive system is a hot issue of current concern. In this paper, firstly, we design the interactive system of university English teaching based on the middle dense vector, knowledge embedding vector, learning feature vector, and other letter cores of fused interactive information, implement the interactive interaction system and debug it. Then the index system is constructed based on the evaluation data of English majors and students in a Normal University on university English teaching materials. Finally, the university English teaching materials evaluation grade data analysis uses a multilayer perceptron neural network. The results showed that the accuracy rate of nine indicators was 73.56%~80.36% for excellent evaluation grade, 86.23%~88.53% for good evaluation grade, and 63.96%~69.43% for average evaluation grade. The accuracy rate of good evaluation grades is higher than the other two categories. This study comprehensively and accurately analyzes the text evaluation of college English textbooks by English majors and students in central China; this university to improve the applicability and group of college English textbooks in a targeted way and promote the improvement of the teaching quality of college English courses in universities.

Design of a text evaluation and interaction system for university English textbooks based on a perceptual machine model in the context of globalization

Applied Mathematics and Nonlinear Sciences

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

In the globalization of big data, how to use big data technology to evaluate the text of college English teaching materials and design the interactive system...

Design of a text evaluation and interaction system for university English textbooks based on a perceptual machine model in the context of globalization

Online veröffentlicht: 14. Aug. 2023

Seitenbereich: -

Eingereicht: 24. Sept. 2022

Akzeptiert: 22. Feb. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00181

Schlüsselwörter
Big data technology, Multilayer perceptron, Neural network model, Feature vector, Interactive system

© 2023 Wanrong Lei, published by Sciendo

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

Design of a text evaluation and interaction system for university English textbooks based on a perceptual machine model in the context of globalization

Online veröffentlicht: 14. Aug. 2023

Seitenbereich: -

Eingereicht: 24. Sept. 2022

Akzeptiert: 22. Feb. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00181

SchlüsselwörterBig data technology, Multilayer perceptron, Neural network model, Feature vector, Interactive system

© 2023 Wanrong Lei, published by Sciendo

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

Schlüsselwörter
Big data technology, Multilayer perceptron, Neural network model, Feature vector, Interactive system