EUVIMEDEUVIMED entdecken
Crossref

KLASIFIKASI TINGKAT RISIKO PENYEBARAN COVID-19 DI PROVINSI INDONESIA MENGGUNAKAN ALGORITMA NAÏVE BAYES

Taufiq Nurhidayat, Halimah Halimah

Jurnal SIMADA (Sistem Informasi dan Manajemen Basis Data) · 30.06.2026 · 8 (1) · 40-47

DOI: 10.30873/simada.v8i1.1337 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Jurnal SIMADA (Sistem Informasi dan Manajemen Basis Data), online erschienen am 30.06.2026. Verfasst von Taufiq Nurhidayat und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid spread of COVID-19 across Indonesian provinces has created significant challenges for government authorities indetermining appropriate mitigation priorities. Accurate classification of regional risk levels is therefore essential to supporteffective decision-making. This study aims to classify the risk level of COVID-19 transmission in Indonesian provinces using theNaïve Bayes algorithm based on publicly available data from the KawalCOVID-19 dataset. The dataset consists of daily confirmedcases aggregated at the provincial level and is processed through data cleaning, normalization, and feature selection stages. Risklevels are categorized into low, medium, and high classes based on cumulative cases and daily case growth indicators. The NaïveBayes classifier is applied due to its simplicity and effectiveness in handling probabilistic classification problems. Modelperformance is evaluated using k-fold cross-validation and standard classification metrics, including accuracy, precision, recall,and confusion matrix analysis. The experimental results indicate that the proposed model is able to classify provincial COVID-19risk levels with satisfactory accuracy, demonstrating consistent performance across validation folds. The findings show that NaïveBayes can effectively capture patterns in COVID-19 case distribution and growth trends among provinces. Compared to previousstudies, such as Azhari et al. (2023) who applied K-Means Clustering and Gunawan & Purwayoga (2022) who used K-Means forCOVID-19 spread analysis, this study offers a supervised classification approach that produces more interpretable and labelspecific risk categories. Moreover, while Thaib & Betrisandi (2025) demonstrated Naïve Bayes effectiveness for respiratory diseaseclassification at the patient level, this study extends its application to provincial-scale epidemiological risk mapping. In conclusion,this study provides a practical and interpretable data mining approach that can assist policymakers in identifying high-risk regionsand prioritizing public health interventions during pandemic conditions

Zitieren

APA

Nurhidayat, T., & Halimah, H. (2026). KLASIFIKASI TINGKAT RISIKO PENYEBARAN COVID-19 DI PROVINSI INDONESIA MENGGUNAKAN ALGORITMA NAÏVE BAYES. Jurnal SIMADA (Sistem Informasi dan Manajemen Basis Data), 8(1), 40-47. https://doi.org/10.30873/simada.v8i1.1337

Vancouver

Nurhidayat T, Halimah H. KLASIFIKASI TINGKAT RISIKO PENYEBARAN COVID-19 DI PROVINSI INDONESIA MENGGUNAKAN ALGORITMA NAÏVE BAYES. Jurnal SIMADA (Sistem Informasi dan Manajemen Basis Data). 2026;8(1):40-47. doi:10.30873/simada.v8i1.1337

BibTeX
@article{Nurhidayat2026,
  author = {Nurhidayat, Taufiq and Halimah, Halimah},
  title = {KLASIFIKASI TINGKAT RISIKO PENYEBARAN COVID-19 DI PROVINSI INDONESIA MENGGUNAKAN ALGORITMA NAÏVE BAYES},
  journal = {Jurnal SIMADA (Sistem Informasi dan Manajemen Basis Data)},
  year = {2026},
  volume = {8},
  number = {1},
  pages = {40--47},
  doi = {10.30873/simada.v8i1.1337}
}
Kostenlos starten →