A Personalized English Teaching Model Based on Big Data and Intelligent Platform Empowerment

This study focuses on constructing and applying a big data-based personalized college English teaching (CET) model under the empowerment of an intelligent platform, aiming to improve CET's quality and effect through data-driven teaching innovation. First, the study analyzes deeply the individualized needs in the CET, and clarifies the differences among students in learning style, interest preference, knowledge base, and learning ability. A complete framework from data collection to teaching implementation is constructed accordingly. The framework uses intelligent platforms to collect multi-dimensional data such as students' learning behavior, grades and interactive records in real time. It generates learning portraits that reflect students' learning patterns and characteristics through data cleaning, preprocessing, data mining, and machine learning techniques. Then, a personalized teaching plan is formulated. Finally, the intelligent platform transforms the plan into a specific teaching practice, providing students with customized learning resources and paths. Taking the School of Foreign Languages at a normal university as a case study, this model is applied in classroom teaching, autonomous learning, after-school counseling, and learning evaluation. Student data is analyzed through data mining techniques, including the K-Means clustering algorithm, the Apriori algorithm, and the C4.5 decision tree model. The proposed mode provides targeted teaching resources and exercises for students with different learning levels. Experimental results indicate that the experimental group using this personalized teaching model outperforms the control group in academic performance, homework completion quality, classroom participation, and other areas. Moreover, students show high satisfaction with various aspects of the teaching, particularly in teaching methods, resources, classroom interaction, and learning support services.