Quality Improvement Model of English Teaching in Universities Based on Big Data Mining

Abstract

Big data mining in English teaching revolutionizes language instruction by leveraging vast amounts of data to personalize and optimize learning experiences. This approach utilizes sophisticated algorithms to analyze learners' language usage patterns, comprehension levels, and areas of difficulty. This paper presents a novel Quality Improvement Model of English Teaching (QIMET) tailored for universities, integrating big data mining techniques with a Stacked Hashing Edge Computing Model (SHECM). Recognizing the importance of enhancing English language proficiency among university students, particularly in an increasingly globalized educational landscape, this research aims to optimize English teaching methodologies through advanced computational approaches. The proposed QIMET framework leverages big data mining to analyze extensive datasets of student performance, language usage patterns, and instructional effectiveness. By extracting valuable insights from these datasets, educators can identify areas for improvement, tailor teaching materials, and personalize learning experiences to meet individual student needs. Simulation analysis of Across a dataset of 500 university students enrolled in English language courses, QIMET achieves an average improvement of 30% in language proficiency scores compared to traditional teaching methods. Moreover, specific language skills exhibit notable enhancements, with vocabulary acquisition increasing by 25%, grammar comprehension by 20%, and communication skills by 35%. The integration of the SHECM enhances the computational efficiency and scalability of the QIMET framework. Real-time data processing and analysis enable educators to make timely interventions and adjustments to teaching strategies, resulting in more responsive and effective English language instruction.