Determining student satisfaction levels in online learning during the Covid-19 pandemic using the K-Medoids algorithm

• Main Authors: Aria, Ririn Restu, Susilowati, Susi, Susliansyah, Susilowati, Isnurrini Hidayat, Soraya, Iin
• Format: Conference Proceeding
• Language: English
• Subjects: Algorithms; Clusters; Coronaviruses; COVID-19; Data mining; Data processing; Distance learning; Education; Pandemics
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/5.0128978

The coronavirus that has spread throughout the world has an impact on all sectors of life, including the world of education, which results in the teaching and learning process cannot run normally and requires changes in the delivery of learning carried out by lecturers to students. For teaching and learning activities to continue, material delivery is carried out online either by using special learning applications or using online learning support media such as zoom, google classroom, and so on. This study aims to determine student satisfaction when carrying out online learning using the K-Medoids method to cluster data obtained from 213 student respondents conducted in April 2021. Data processing is done by providing 14 questions related to online learning methods and methods are then grouped and analyzed using K-Medoids data mining to produce 4 clusters, namely the cluster strongly agrees with 22 respondents, the cluster agrees with 103 respondents, the cluster strongly disagrees with 73 respondents and the cluster disagrees with 15 respondents. With this research, it is hoped that they can find out about the grouping of student satisfaction with online learning that is currently taking place so that it can further improve the quality of the learning process carried out during the Covid-19 pandemic that occurred in Indonesia, especially in higher education.