Research on Personalized English Language Learning Based on Artificial Intelligence

Abstract

Although AI technology has been widely utilized in many fields and has reaped good reviews. However, there is a vacancy in the education field for AI technology to achieve personalized recommendations for the English language. In this paper, based on the traditional cognitive diagnostic model, we propose optimizing two aspects, namely question type and mastery state. Combining the neighborhood recommendation algorithm, the English learning recommendation model is constructed using fuzzy cognitive diagnosis. Based on the theory of adaptive learning, we have designed a personalized bank of recommended English learning questions. The model is utilized in the real world of English learning, and a control experiment is designed to evaluate the student’s knowledge mastery and the impact of the model application. The experiment shows that student A has a better mastery of S1 and S3, with mastery levels of 0.856 and 0.815, respectively, but only 0.235 for S4, and needs to customize a more targeted personalized learning plan and strategy for S4-related content. The average scores of D1 and D2 before practice were 73.51 and 72.18, and after practicing through the personalized recommending English learning methods proposed in this paper, the English score of the D2 class was improved to 85.33, and the t-test result between the two groups was significant p-value of 0.002, which is less than 0.01, indicating that there is a significant difference between the two groups and that the model proposed in this paper has a significant enhancement on English learning.

Keywords

• fuzzy cognitive diagnosis
• neighborhood recommendation algorithm
• adaptive learning
• personalized recommendation
• english learning
• 97b20