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

<p>Analyzing students’ feedback course text data is an inevitable requirement to improve the teaching quality of English language courses in colleges and universities. Based on the two parts of word vector representation and recognition of text language in natural language technology, this paper completes the word vector representation of English language course text in colleges and universities through the CBOW and Skip-gram structure of World2Vec model. Using the LDA topic model, the obtained English language word vectors are identified, and then the English language course system of colleges and universities is processed to complete the optimization of the course system. On this basis, 10 English language courses of X university are selected and the texts of question responses and course evaluations of the selected English language courses are collected and analyzed using the model. The study shows that 80% of the course responses are active at the beginning and end of the question life cycle. The percentage of question responses decreased as the number of questions increased. Students in Majors A (53%) and B (27%) were more concerned about teaching ability, and students in Majors B (40%) and C (57%) were more concerned about teaching style. Based on the above analysis, pedagogues can optimize the teaching quality of English courses in colleges and universities in terms of teaching ability and teaching style.</p>
</abstract>

Analyzing students’ feedback course text data is an inevitable requirement to improve the teaching quality of English language courses in colleges and universities. Based on the two parts of word vector representation and recognition of text language in natural language technology, this paper completes the word vector representation of English language course text in colleges and universities through the CBOW and Skip-gram structure of World2Vec model. Using the LDA topic model, the obtained English language word vectors are identified, and then the English language course system of colleges and universities is processed to complete the optimization of the course system. On this basis, 10 English language courses of X university are selected and the texts of question responses and course evaluations of the selected English language courses are collected and analyzed using the model. The study shows that 80% of the course responses are active at the beginning and end of the question life cycle. The percentage of question responses decreased as the number of questions increased. Students in Majors A (53%) and B (27%) were more concerned about teaching ability, and students in Majors B (40%) and C (57%) were more concerned about teaching style. Based on the above analysis, pedagogues can optimize the teaching quality of English courses in colleges and universities in terms of teaching ability and teaching style.

Optimization of English Language Curriculum System in Colleges and Universities Based on Natural Language Processing Technology

Applied Mathematics and Nonlinear Sciences

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

Analyzing students’ feedback course text data is an inevitable requirement to improve the teaching quality of English language courses in colleges and...

Optimization of English Language Curriculum System in Colleges and Universities Based on Natural Language Processing Technology

Online veröffentlicht: 31. Jan. 2024

Seitenbereich: -

Eingereicht: 20. Dez. 2023

Akzeptiert: 28. Dez. 2023

DOI: https://doi.org/10.2478/amns-2024-0239

Schlüsselwörter
World2Vec model, LDA topic model, Natural language processing technology, College English courses

© 2024 Xiaona Ma et al., published by Sciendo

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

Optimization of English Language Curriculum System in Colleges and Universities Based on Natural Language Processing Technology

Online veröffentlicht: 31. Jan. 2024

Seitenbereich: -

Eingereicht: 20. Dez. 2023

Akzeptiert: 28. Dez. 2023

DOI: https://doi.org/10.2478/amns-2024-0239

SchlüsselwörterWorld2Vec model, LDA topic model, Natural language processing technology, College English courses

© 2024 Xiaona Ma et al., published by Sciendo

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

Schlüsselwörter
World2Vec model, LDA topic model, Natural language processing technology, College English courses