PERBANDINGAN ALGORITMA MACHINE LEARNING UNTUK DETEKSI BERITA HOAKS DI MEDIA SOSIAL

Authors

  • Nadine Viga Septira Fakultas Teknik, Universitas Krisnadwipayana, Jakarta
  • Elmi Devia Fakultas Teknik, Universitas Krisnadwipayana, Jakarta
  • Harry Dwiyana Kartika Fakultas Teknik, Universitas Krisnadwipayana, Jakarta

DOI:

https://doi.org/10.35316/jimi.v11i2.10754

Keywords:

Machine Learning, fake news, Algoritma Naïve Bayes, Support Vector Machine, Random Forest, TF-IDF

Abstract

The spread of fake news on social media can influence public opinion and cause misunderstandings. This study aims to compare the performance of the Naive Bayes, Support Vector Machine (SVM), and Random Forest algorithms in classifying fake news and real news. The dataset consists of 1,600 news articles, including 800 real news articles and 800 fake news articles. The research process includes data labeling, preprocessing (case folding, text cleaning, and whitespace normalization), feature extraction using Term Frequency–Inverse Document Frequency (TF-IDF), an 80:20 training-testing split, and hyperparameter tuning using GridSearchCV with five-fold cross-validation. Model performance was evaluated using accuracy, precision, recall, F1-score, and a confusion matrix. The results show that Naive Bayes achieved the best performance among the three algorithms, with an accuracy of 95.31%, precision of 94.83%, recall of 96.49%, and an F1-score of 95.65%. This study is limited to a dataset of 1,600 news articles, three classification algorithms, and TF-IDF feature extraction. Furthermore, GridSearchCV was not compared with other hyperparameter optimization methods. In practical terms, these findings can serve as a reference for selecting an algorithm for fake news detection, while the best-performing model, implemented in a Streamlit prototype, can serve as an initial tool for automated news classification.

Downloads

Download data is not yet available.

References

[1] R. R. Sani, Y. A. Pratiwi, S. Winarno, D. E. Udayanti, and F. Al Zami, “Comparative Analysis of the Naive Bayes Classifier Algorithm and Support Vector Machine for Hoax Classification in Indonesian Online News,” Jurnal Masyarakat Informatika, vol. 13, no. 2, pp. 85–98, 2022.

[2] A. H. Dalimunthe, M. Ula, and R. Meiyanti, “Unjuk Kerja Algoritma Support Vector Machine (SVM) dan Naïve Bayes dalam Pengklasifikasian Berita Hoaks pada Twitter tentang Aksi Cepat Tanggap (ACT),” Jurnal Elektronika dan Teknologi Informasi, vol. 5, no. 2, pp. 11–22, 2024.

[3] U. Karimah and Z. Fatah, “Klasifikasi Berita Hoaks di Media Sosial Menggunakan Algoritma Naive Bayes dan RapidMiner,” JISCO: Journal of Information System and Computing, vol. 3, no. 2, pp. 55–65, 2025, doi: 10.30631/jisco.v3i2.4028.

[4] A. K. Aziz and J. W. Kusuma, “Penerapan Machine Learning untuk Deteksi Hoaks di Media Sosial Indonesia: Systematic Literature Review,” CESS (Journal of Computer Engineering, System and Science), vol. 10, no. 2, pp. 608–616, 2025, doi: 10.24114/cess.v10i2.66584.

[5] M. D. Desriansyah, I. U. Sari, and Z. Zulfahmi, “Analisis Efektivitas Algoritma Machine Learning dalam Deteksi Hoaks: Pada Berita Digital Berbahasa Indonesia,” Jurnal Sistem Informasi dan Informatika, vol. 3, no. 2, pp. 63–69, 2025.

[6] N. Maulana, M. R. Handayani, W. D. Yuniarti, and K. Umam, “Penerapan Metode Support Vector Machine dalam Mengklasifikasikan Berita Politik: Fakta vs Hoaks,” JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), vol. 10, no. 3, pp. 2679–2688, 2025, doi: 10.29100/jipi.v10i3.8077.

Published

12-11-2026

How to Cite

Septira, N. V., Devia, E., & Kartika, H. D. (2026). PERBANDINGAN ALGORITMA MACHINE LEARNING UNTUK DETEKSI BERITA HOAKS DI MEDIA SOSIAL. Jurnal Ilmiah Informatika, 11(2), 165–170. https://doi.org/10.35316/jimi.v11i2.10754

Similar Articles

1 2 3 4 5 6 7 > >> 

You may also start an advanced similarity search for this article.