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

<p>The article first discusses the categorization and difficulty of learning resources and proposes a method to quantify the difficulty of teaching resources. Then, the article recommends appropriate learning resources through similarity matching and student knowledge level diagnosis. This includes analyzing students’ test answers and modeling students’ knowledge level based on this. Data analysis and model building were employed to propose four key indicators: knowledge point density, knowledge point depth, evaluation index and correctness rate. In addition, cosine distance was employed to measure the similarity between resources and Hidden Markov Models were used to predict students’ knowledge point mastery. Four key indicators were effectively applied to construct a vector of resource difficulty indicators in quantifying learning resource difficulty. A vector representation of students’ knowledge mastery was successfully built in diagnosing students’ knowledge level. In addition, the article discusses the construction of a personalized learner preference model and a personalized English teaching model based on collaborative filtering algorithms. The effect of college English teaching can be effectively improved through the detailed Analysis of learning resources and the application of personalized recommendation model.</p>
</abstract>

The article first discusses the categorization and difficulty of learning resources and proposes a method to quantify the difficulty of teaching resources. Then, the article recommends appropriate learning resources through similarity matching and student knowledge level diagnosis. This includes analyzing students’ test answers and modeling students’ knowledge level based on this. Data analysis and model building were employed to propose four key indicators: knowledge point density, knowledge point depth, evaluation index and correctness rate. In addition, cosine distance was employed to measure the similarity between resources and Hidden Markov Models were used to predict students’ knowledge point mastery. Four key indicators were effectively applied to construct a vector of resource difficulty indicators in quantifying learning resource difficulty. A vector representation of students’ knowledge mastery was successfully built in diagnosing students’ knowledge level. In addition, the article discusses the construction of a personalized learner preference model and a personalized English teaching model based on collaborative filtering algorithms. The effect of college English teaching can be effectively improved through the detailed Analysis of learning resources and the application of personalized recommendation model.

Correlation Analysis and Teaching Optimization of University English Lecture Mode Preferences

Department of College English II, School of Foreign Studies

Applied Mathematics and Nonlinear Sciences

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

The article first discusses the categorization and difficulty of learning resources and proposes a method to quantify the difficulty of teaching resources....

Correlation Analysis and Teaching Optimization of University English Lecture Mode Preferences

Online veröffentlicht: 26. Feb. 2024

Seitenbereich: -

Eingereicht: 15. Jan. 2024

Akzeptiert: 25. Jan. 2024

DOI: https://doi.org/10.2478/amns-2024-0584

Schlüsselwörter
Collaborative filtering algorithm, Similarity matching, Knowledge level diagnosis, Student preference, English instruction

© 2024 Zhenzhen Wang, published by Sciendo

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

Correlation Analysis and Teaching Optimization of University English Lecture Mode Preferences

Online veröffentlicht: 26. Feb. 2024

Seitenbereich: -

Eingereicht: 15. Jan. 2024

Akzeptiert: 25. Jan. 2024

DOI: https://doi.org/10.2478/amns-2024-0584

SchlüsselwörterCollaborative filtering algorithm, Similarity matching, Knowledge level diagnosis, Student preference, English instruction

© 2024 Zhenzhen Wang, published by Sciendo

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

Schlüsselwörter
Collaborative filtering algorithm, Similarity matching, Knowledge level diagnosis, Student preference, English instruction