Student Clustering Through KMeans to Enhance Teaching

Learning strategies play a vital role in education, and focusing on teaching methods may promote the development of process-oriented competencies. Educators are looking for ways to improve the effectiveness of online education platforms to ensure the highest quality of learning experience. This study focuses on analyzing and understanding students' performance in online education settings and utilizes advanced clustering techniques and educational exercise models to optimize pedagogical strategies and improve overall quality, particularly in electronic education. The research groups students based on three variables of their interaction with exercises—time spent, number of attempts, and grade obtained in the exercises—using artificial intelligence algorithms. The k-means algorithm was applied to eight educational exercises in Moodle, using data from Zenodo.org, resulting in six clusters each. The findings revealed student patterns, identified problems in exercise features, and suggested exercise redesigns applicable to e-learning assessments to measure student knowledge acquisition.