Application of the K-Means Clustering Algorithm to Determine Student Academic Ability Levels during Covid-19

Abstract

Since the existence of the COVID-19 pandemic in Indonesia, various ways and efforts have been made by the government to prevent the spread of the corona virus. One of them is by implementing an online learning system, so that it causes differences in the learning process that is usually carried out by lecturer face to face with students. Changes in the learning process are expected to be carried out effectively and efficiently. The purpose of this research is to find out how the level of students' academic ability is during online learning in the Informatics Engineering study program at Universitas Malikussaleh and aims to produce a system model that can cluster the level of student academic ability using the K-Means Clustering Algorithm. The variables used in this study are 3 parameters, namely the teaching and learning process, facilities and infrastructure and learning outcomes. The stages carried out in this study were collecting questionnaire data filled out by 200 students. The data obtained would be processed using the K-Means Clustering Algorithm and forming 3 clusters, namely low, medium and high. The clustering results of 200 data obtained 27 students having low academic ability levels (Cluster 1), 87 students having moderate academic ability levels (Cluster 2) and as many as 86 students having high academic ability levels (Cluster 3). The contribution of this research is to help the management of the Informatics Engineering Study Program at Universitas Malikussaleh to find out how the level of student academic ability is during the online learning period during the COVID-19 pandemic, so that evaluation of learning can be carried out online.