Decision Support System for Classifying Bullying Victims Using Website-Based C4.5 Algorithm

Fransiska Nabila Ariesha; Melka Andriana; Yunita Marien; Ardiyansyah; Yeni Mustika

doi:10.59934/jaiea.v5i3.2474

Authors

Fransiska Nabila Ariesha Universitas Bina Sarana Informatika
Melka Andriana Universitas Bina Sarana Informatika
Yunita Marien Universitas Bina Sarana Informatika
Ardiyansyah Universitas Bina Sarana Informatika
Yeni Mustika Universitas Bina Sarana Informatika

DOI:

https://doi.org/10.59934/jaiea.v5i3.2474

Keywords:

Bullying Classification; C4.5 Algorithm; Decision Support System; Machine Learning; Website

Abstract

Bullying remains a serious problem in Indonesian schools, where Indonesia ranks highest in ASEAN with a bullying rate of 84%. Early detection of bullying victims is critical for timely intervention by school counselors (BK teachers). This study develops a web-based Decision Support System (DSS) that integrates the C4.5 decision tree algorithm to classify students at risk of becoming bullying victims. The system uses the Bullying 2018 with Labels dataset from Kaggle containing 22,766 student records with eight input attributes and four output classes: Ringan (Mild), Sedang (Moderate), Berat (Severe), and Sangat Berat (Very Severe). The C4.5 model is implemented in Python using scikit-learn with entropy criterion and validated through 10-fold cross validation, achieving an accuracy of 99.94%. The model is deployed as a Flask REST API and integrated with a PHP CodeIgniter 3 web frontend and MySQL database. The system allows BK teachers to input student behavioral data and receives instant risk classification results. Usability testing confirmed the system is effective, efficient, and satisfying to use. This DSS provides an objective, data-driven tool to support early identification and handling of bullying cases in schools.

Downloads

Download data is not yet available.

References

F. Ali, C. Ariesty, L. Lauren, R. Wulandari, and N. Maharani, “BULLYING DI SEKOLAH DASAR,” vol. 1, no. 4, pp. 496–504, 2022.

R. A. Safaat, “Tindakan Bullying di Lingkungan Sekolah yang Dilakukan Para Remaja,” vol. 1, no. 2, pp. 97–100, 2023.

M. I. Djamzuri and A. P. Mulyana, “Fenomena Bullying Dalam Mendorong Kebijakan Literasi Berbasis AI ( Artificial Intelligence ) Pada Teknologi Media Baru,” vol. 3, pp. 1304–1312, 2023.

Y. E. Nizmi, D. A. Hanif, R. Anjelli, and M. R. Pratama, “Penerapan Fenomena Bullying pada Tingkat Sekolah Dasar dan Menengah di Desa Banjar Seminai Tahun 2024,” pp. 606–619, 2024.

Abdillah, “EDUCARE : Jurnal Pendidikan dan Kesehatan Dampak Bullying di Sekolah Dasar dan Pencegahannya,” no. 2021, pp. 102–108, 2024.

W. Widiyawati, E. Mulyani, W. L. Fitrianur, D. D. Musfara, and D. L. Octavia, “PENCEGAHAN DAN PENANGANAN BULLYING,” vol. 7, pp. 92–99, 2025.

R. Hilma, M. Ula, S. Fachrurrazi, M. T. Informasi, and U. Malikussaleh, “Analisis Sentimen Cyberbullying pada Media Sosial Twitter menggunakan Metode Support Vector Machine dan Naïve Bayes Classifier,” pp. 107–123, 2023.

S. A. Mahmudah, A. Yudhistira, F. Teknik, and U. T. Indonesia, “Analisis Sentimen Terhadap Cyberbullying pada Platform Media Sosial X Menggunakan Algoritma Naive Bayes Sentiment Analysis of Cyberbullying on Social Media Platform X Using Naive Bayes Algorithm,” vol. 5, no. 1, pp. 189–200, 2025.

A. M. Alhakim, H. Leonardo, and A. N. Putri, “Analisis Sentimen Terhadap Bullying Di Indonesia Pada Twitter Menggunakan Naïve Bayes dan SVM,” vol. 2, no. 3, pp. 210–218, 2025.

Y. Wahyuningsih, I. Lubis, and K. A. B. Sitepu, “Global Research and Innovation Journal ( GREAT ) IMPLEMENTASI ALGORITMA K-NEAREST NEIGHBOR UNTUK MEMPREDIKSI Masa remaja merupakan fase transisi dari anak-anak menuju dewasa , di mana kondisi psikis sangat labil . Pada masa ini , peran lingkungan sangat d,” vol. 1, pp. 887–893, 2025.

A. Mikaya, Z. Rusdi, M. D. Lauro, S. Informasi, and U. Tarumanagara, “SISTEM PENDUKUNG KEPUTUSAN DALAM PEMILIHAN,” pp. 2–7, 2023.

A. Al Ghifari, P. Irfansyah, and Y. Nugraha, “Dinamika MENGGUNAKAN METODE AHP ( ANALYTICAL Dinamika,” pp. 417–428, 2021.

D. Nisrina, T. Informatika, and U. N. Waluyo, “Analisis Kepuasan Konsumen Menggunakan Metode Algoritma C4 . 5 Berbasis Rapidminer pada PT . Adeaksa,” vol. 9, no. 1, pp. 26–33, 2024.

A. Saburina, Husaini, and Fitriyani, “KULIAH MBKM DI UNIVERSITAS JABAL GHAFUR,” no. 1, pp. 10–17, 2024.

D. Sari, Hardian Oktavianto, and S. Ilham, “Jurnal Smart Teknologi Jurnal Smart Teknologi,” vol. 3, no. 4, pp. 413–422, 2022.