University english teaching evaluation using artificial intelligence and data mining technology

This work intends to drive reform and innovation in English teaching evaluation and support personalized English instruction. It utilizes deep learning (DL) and artificial intelligence (AI)-driven data mining technology to explore a reliable and efficient method for university English teaching evaluation. By employing DL, this work explores innovative English teaching models and introduces a Bayesian framework to enable personalized teaching strategies. In the data mining process, the Transformer architecture is applied to English teaching evaluations. This capitalizes on its powerful feature extraction and sequence modeling capabilities to gain a comprehensive understanding and precise evaluation of students' English proficiency. Additionally, an AI-based method for English teaching evaluation is proposed. Data from the English teaching and evaluation system for Computer Science students in the 2018 class at Tianjin University of Science and Technology are collected, analyzed, and processed. Group profiles of students are created to predict exam outcomes. The findings show that over 70% of students engage in active English learning only occasionally, with a higher proportion among females. More than 80% of males recognize the importance of listening and speaking skills, a sentiment shared by over 90% of female students. In terms of factors influencing students' passing exams, scores in various question types play a central role, significantly impacting final grades. These scores reflect students' mastery of English knowledge and application abilities. This work applies the Transformer architecture from natural language processing to the education domain, achieving interdisciplinary integration and innovation. This cross-disciplinary approach not only enriches teaching assessment methods but also provides new solutions for broader educational challenges. The proposed method enhances the objectivity and accuracy of teaching evaluation, minimizing the influence of human bias assessment results.