Course Evaluation and Improvement Based on Association Rule Mining in English Online Teaching and Learning

Abstract

Association rule mining in English online teaching and learning involves the analysis of patterns and relationships within large sets of data to uncover meaningful insights that can enhance the teaching and learning experience. By examining student interactions, performance data, and usage patterns on online learning platforms, educators can identify correlations between different learning activities, student characteristics, and learning outcomes. This paper explores the application of the Frequent Pattern System Modelling Association Rule (FPSMAR) in the realm of online English teaching and learning. FPSMAR offers a data-driven approach to analyzing student interaction data, uncovering meaningful patterns and associations between different elements of the online learning environment and student outcomes. Through the analysis of association rules and frequent patterns, educators gain valuable insights into effective instructional strategies, learning patterns, and areas for improvement. The study presents association rules indicating relationships such as the correlation between multimedia resource usage and high language proficiency or active online discussion participation and enhanced speaking ability. The study reveals association rules indicating strong relationships, such as a correlation coefficient of 0.80 between multimedia resource usage and high language proficiency, or a confidence level of 0.85 indicating enhanced speaking ability through active online discussion participation.