Clustering Social Media Addiction Levels Among Students Using the K-Means Clustering Algorithm

Muhamad Sandi; Jordy Lasmana Putra; Tyas Setiyorini

doi:10.52958/iftk.v22i2.12605

Authors

Muhamad Sandi Universitas Bina Sarana Informatika
Jordy Lasmana Putra Universitas Bina Sarana Informatika
Tyas Setiyorini Universitas Bina Sarana Informatika

DOI:

https://doi.org/10.52958/iftk.v22i2.12605

Keywords:

Social Media Addiction, K-Means Clustering, Elbow Method, Social Media Behavior, Principal Component Analysis (PCA)

Abstract

Social media has become an integral part of students’ lives, yet excessive use often leads to symptoms of addiction that negatively affect mental health and academic performance. This study aims to cluster the levels of social media addiction among students and university students using the K-Means Clustering algorithm as an unsupervised learning approach. The dataset was obtained from the Kaggle platform, containing variables such as daily usage duration, access frequency, sleep disturbance, and psychological impact. The Elbow Method was employed to determine the optimal number of clusters, while Principal Component Analysis (PCA) was used for visualization. The results grouped respondents into three categories: mild addiction (46.8%), moderate addiction (22.6%), and severe addiction (30.6%). A strong correlation was observed between high access frequency and symptoms such as sleep disruption and decreased concentration. These findings highlight the importance of designing data-driven prevention strategies within educational environments and provide a foundation for further institutional interventions to maintain digital balance among youth.

References

R. Gunawan, S. Aulia, H. Supeno, A. Wijanarko, J. P. Uwiringiyimana, and D. Mahayana, “Adiksi Media Sosial dan Gadget bagi Pengguna Internet di Indonesia,” Techno-Socio Ekon., vol. 14, no. 1, pp. 1–14, 2021, doi: https://doi.org/10.32897/techno.2021.14.1.544

P. Limilia, R. A. Gelgel, and L. R. Rahmiaji, “Digital Literacy Among Z Generation in Indonesia,” pp. 1–11, 2022, doi: https://doi.org/10.15405/epsbs.2022.01.02.1

J. W. Sri Rizki, “Social Media as Tools of Communication and Learning,” QALAMUNA J. Pendidikan, Sos. dan Agama, vol. 15, no. 1, pp. 391–404, 2023, doi: https://doi.org/10.37680/qalamuna.v15i1.2429

T. Amelia, U. H. Zainita, and E. Martha, “Social Media Use Behavior and Social Media Disorder Among Faculty of Public Health Students During the COVID-19 Pandemic,” Kesmas J. Kesehat. Masy. Nas., vol. 18, no. 4, p. 265, Nov. 2023, doi: https://doi.org/10.21109/kesmas.v18i4.6920

M. I. Ciptandini and R. Prathivi, “Klasterisasi Tingkat Kecanduan Penggunaan Tiktok Terhadap Minat Belajar Menggunakan Algoritma K-Means Clustering,” Kesatria J. Penerapan Sist. Inf. (Komputer dan Manajemen), vol. 6, no. 1, pp. 77–84, Jan. 2025, doi: https://doi.org/10.30645/kesatria.v6i1.548

T. Feng et al., “The relationships between mental health and social media addiction, and between academic burnout and social media addiction among Chinese college students: A network analysis,” Heliyon, vol. 11, no. 3, p. e41869, Feb. 2025, doi: https://doi.org/10.1016/j.heliyon.2025.e41869

Z. I. Santini et al., “Social Media Addiction Predicts Compromised Mental Health as well as Perceived and Objective Social Isolation in Denmark: A Longitudinal Analysis of a Nationwide Survey Linked to Register Data,” Int. J. Ment. Health Addict., vol. 23, no. 4, pp. 3136–3153, Aug. 2025, doi: https://doi.org/10.1007/s11469-024-01283-3

A. Nafisah, N. S. Ahmed, T. Balamurugan, K. Gimka, and L. C. Wijaya, “The Effect of Social Media on Students’ School Life in Indonesia,” Acta Pedagog. Asiana, vol. 3, no. 2, pp. 80–90, 2024, doi: https://doi.org/10.53623/apga.v3i2.426

D. File, B. File, B. Bőthe, M. D. Griffiths, and Z. Demetrovics, “Investigating mental representations of psychoactive substance use and other potentially addictive behaviors using a data driven network-based clustering method,” PLoS One, vol. 18, no. 10 October, pp. 1–19, 2023, doi: https://doi.org/10.1371/journal.pone.0287564

B. Roter, N. Ninkovic, and S. V. Dordevic, “Clustering superconductors using unsupervised machine learning,” Phys. C Supercond. its Appl., vol. 598, p. 1354078, Jul. 2022, doi: https://doi.org/10.1016/j.physc.2022.1354078

Q. Zhou, Y. Lei, H. Du, and Y. Tao, “Public concerns and attitudes towards autism on Chinese social media based on K-means algorithm,” Sci. Rep., vol. 13, no. 1, p. 15173, Sep. 2023, doi: https://doi.org/10.1038/s41598-023-42396-4

J. Packer and M. Flack, “The Role of Self-Esteem, Depressive Symptoms, Extraversion, Neuroticism and FOMO in Problematic Social Media Use: Exploring User Profiles,” Int. J. Ment. Health Addict., vol. 22, no. 6, pp. 3975–3989, Dec. 2024, doi: https://doi.org/10.1007/s11469-023-01094-y

S. V. Oprea and A. Bâra, “Assessing the Dual Impact of the Social Media Platforms on Psychological Well-being: A Multiple-Option Descriptive-Predictive Framework,” Comput. Econ., no. 6, 2024, doi: https://doi.org/10.1007/s10614-024-10717-y

I. Trulson, S. Holdenrieder, and G. Hoffmann, “Using machine learning techniques for exploration and classification of laboratory data,” J. Lab. Med., vol. 48, no. 5, pp. 203–214, Oct. 2024, doi: https://doi.org/10.1515/labmed-2024-0100

I. Zada et al., “Performance Evaluation of Simple K -Mean and Parallel K -Mean Clustering Algorithms: Big Data Business Process Management Concept,” Mob. Inf. Syst., vol. 2022, 2022, doi: https://doi.org/10.1155/2022/1277765

M. G. Pradana, P. H. Saputro, A. Mualo, A. Faizah, and W. F. Zalmi, “Semantic clustering of scientific abstracts with transformer embeddings and traditional text representations,” International Journal of Advances in Applied Sciences, vol. 15, no. 2, p. 532, Jun. 2026, doi: https://doi.org/10.11591/ijaas.v15.i2.pp532-540

D. Listianing Tyas and L. Charifi, “Forecasting Monthly Sales Using Single Exponential Smoothing: An Evaluation and Performance Analysis,” Journal of Computing Innovations and Emerging Technologies, vol. 1, no. 1, pp. 11–15, Jul. 2025, doi: https://doi.org/10.64472/jciet.v1i1.3