Rancang Bangun Sistem TOEFL Untuk Analisis Kelemahan Peserta Dengan Penerapan Algoritma K-Means Clustering

Abstract

English proficiency is a critical skill across various sectors, particularly in educational and professional contexts. The TOEFL test assesses English language skills, covering aspects such as Reading, Listening, Speaking, and Writing. However, TOEFL results often only provide a total score without detailed insights into participants' weaknesses. To address this, this study utilizes the K-Means Clustering algorithm for its simplicity, efficiency in processing multidimensional data, and ability to produce statistically meaningful groupings. The research aims to identify the weaknesses of TOEFL participants at the Language Laboratory of ITN Malang. The dataset comprises scores from 520 students across Reading, Structure and Written Expression, and Listening sections. This method classifies participants into three primary clusters: Reading Boosters (C1), Grammar Builders (C2), and Listening Improvers (C3). The clustering process involves randomly selecting initial centroids, calculating distances using the Euclidean Distance formula, and iterating until cluster stability is achieved. The analysis results show that 36.54% of participants fall into C1, 41.35% into C2, and 22.21% into C3. The implementation of this algorithm offers valuable insights for developing more effective learning programs.