Penerapan Algoritma K-Means untuk Mengidentifikasi Minat Belajar Siswa di Sekolah Dasar Negeri Puu Naga

Abstract

Elementary education is the fundamental stage in shaping students’ character, attitudes, and learning motivation. Learning interest plays a vital role in determining students’ success in understanding and mastering the lessons. However, differences in background, abilities, and learning styles often cause significant variations in students’ interest. Therefore, it is necessary to apply an analytical method that can group students based on their level of learning interest so that teachers can provide appropriate learning strategies. This study aims to implement the K-Means Clustering algorithm to identify the learning interest of students at Sekolah Dasar Negeri Puu Naga. The research method used is a quantitative approach with data collected through questionnaires consisting of several indicators of learning interest, such as perseverance in completing assignments, enthusiasm during lessons, attention to teacher explanations, and participation in class activities. The collected data were then analyzed using the K-Means algorithm to form several clusters of learning interest. The data processing stages included determining the number of clusters, selecting the initial centroid, calculating the distance of data to the centroid, grouping data, and iterating until a stable clustering result was achieved. The results of the study show that the K-Means algorithm successfully grouped students into three main categories, namely high, medium, and low learning interest. Students in the high-interest group consistently demonstrated active learning behavior and strong intrinsic motivation, while those in the medium group showed fluctuating interest influenced by external factors such as the learning environment and teaching methods. Meanwhile, students in the low-interest group displayed a lack of attention and motivation, thus requiring special interventions. These findings provide valuable insights for the school, especially teachers, in designing adaptive and personalized teaching strategies. In conclusion, the application of the K-Means algorithm is proven effective as an analytical tool to identify students’ learning interest.