Big Data Analysis and Teaching Model Exploration of English Education in a Mobile Learning Environment

Abstract

Mobile learning is transforming English language learning, providing accessibility and flexibility. Students can participate anywhere, anytime, through application and interactive experiments. Adaptive technology improves understanding and retention by adapting content to the needs of each user. Aim: The main objective of this study is to develop an intelligent strategy for optimizing English education in a mobile learning environment through big data analysis and learning model analysis. Methodology: In this study we propose a novel method called as Zebra Search-driven Optimal Adaptive Boosting (ZS-OAdaBoost) algorithm to enhance students’ English language speaking fluency. To pre-process the collected raw data, a data normalization technique is executed out. The needs of the students, the instructional requirements, and the online learning objectives of a college English education are examined. Big data analysis is utilized to extract insights from the data to train our proposed model. Zebra Search is employed to optimize feature selection and weight assignment, enhancing model performance. Research findings: The proposed model implemented in Python software. In the evaluation phase, we meticulously evaluate the efficacy of our suggested ZS-OAdaBoost model in recognizing diverse aspects of English learning across diverse parameters. Our experimental findings undeniably showcase the superior performance of our model compared to existing methods. Significantly, we observed notable improvements in accuracy and robustness, particularly when adapting to dynamic learning conditions. Conclusion: This study highlights the benefits of big data analytics and novel algorithms for improving English language teaching in mobile learning environments.