Application Of K-Means Algorithm to Cluster Students' Reading Patterns in the Digital Age

Abstract

This study aims to group students' reading patterns in the digital era using the K-Means algorithm. This algorithm divides data into clusters, such as reading duration, type of reading, reading frequency, and devices used. Data were obtained through questionnaires distributed to 224 students of SMK Negeri 4 Bandar Lampung, with 214 valid data analysed after the preprocessing stage. The selection of vocational high school students as this study was based on previous journal references that examined reading patterns in PAUD to SMA students, so special attention is paid to vocational high school students, understanding reading patterns that have different needs compared to references with other levels of education. The clustering process produced four clusters with unique characteristics, reflecting differences in reading patterns based on the type of media used, intensity, and digital devices. The results of the study showed that clusters with high digital reading intensity can be directed to utilise e-books and online learning platforms optimally, while clusters with a preference for printed books require strengthening physical reading habits through literacy activities. With a Davies-Bouldin index value of -2.224, the quality produced is proven to be very good. These findings provide guidance for educators to develop technology-based education policies and personal approaches to improving student literacy. Designing learning programs with methods and student reading patterns to support the quality of education in the digital era.