The Application of Naive Bayes in Analyzing Public Sentiment Toward the Performance of the North Sumatra Regional Government in Handling Flash Floods

Rivaldo Siburian; Rikki Josua Tampubolon; Valentino Surbakti; M. Irvandy Haris; Rizky Rahmansyah

doi:10.55927/fjcis.v5i1.16417

Authors

Rivaldo Siburian Universitas Prima Indonesia
Rikki Josua Tampubolon Universitas Prima Indonesia
Valentino Surbakti Universitas Prima Indonesia
M. Irvandy Haris Universitas Prima Indonesia
Rizky Rahmansyah Universitas Prima Indonesia

DOI:

https://doi.org/10.55927/fjcis.v5i1.16417

Keywords:

Sentiment Analysis, Naive Bayes, Flash Flood, Government Performance

Abstract

This study analyzes public sentiment towards the performance of the North Sumatra Regional Government in handling flash floods using the Multinomial Naive Bayes algorithm. A total of 1,132 opinion data points were collected from social media and news portals through web crawling from November 2025 to February 2026. Sentiment labeling was performed using a lexicon-based approach with the InSet dictionary. Classification results showed a dominance of negative sentiment at 88.4%, focusing on slow emergency response. Model evaluation with an 80:20 data split yielded 89.43% accuracy and an F1-Score of 0.844 for Naive Bayes, while SVM achieved the highest F1-Score (0.855). This study concludes that AI-based sentiment analysis can serve as an objective instrument for government performance auditing.

Downloads

Download data is not yet available.

References

Akbar, A. M., & Qoiriah, A. (2025). Analisis Sentimen Berbasis Aspek Kinerja Pemerintah Kota Surabaya Menggunakan Algoritma Naïve Bayes. Journal Of Informatics And Computer Science (Jinacs), 7(02), 539–545.

Amalia, N. L. (2023). Analisis Sentimen Pada Perpindahan Ibukota Indonesia Dengan Algoritma Support Vector Machine: Evaluasi Leksikon, Metode Ekstraksi Fitur, Dan Kernel Trick. Fakultas Sains Dan Teknologi Universitas Islam Negeri Syarif Hidayatullah.

Desta, P. R. (2025). Responsivitas Kepala Pelaksana Badan Penanggulangan Bencana Daerah Dalam Menanggulangi Bencana Alam (Studi Kasus Pada Kota Bandar Lampung).

Fadhillah, O. S. D., Jaman, J. H., & Carudin, C. (2025). Perbandingan Naive Bayes, Support Vector Machine, Logistic Regression Dan Random Forest Dalam Menganalisis Sentimen Mengenai Tiktokshop. Jurnal Informatika Dan Teknik Elektro Terapan, 13(1).

Febriana, K. A., Watie, E. D. S., Fanani, F., & Setiawan, Y. B. (2025). Media Sosial Dan Transformasi Komunikasi Publik: Dari Opini Hingga Mitigasi Bencana. Penerbit Mitra Cendekia Media.

Helmi Setyawan, M. Y., Herwanto, P., & Wiharko, T. (2025). Machine Learning: Memahami Multinomial, Distribusi Probabilitas & Multinomial Naive Bayes. Tangguh Denara Jaya Publisher.

Jalili, A., Tabrizchi, H., Mosavi, A., & Varkonyi-Koczy, A. R. (2024). Enhancing Language Model Performance With A Novel Text Preprocessing Method. Acta Physica Polonica: A, 146(4).

Kadam, T., & Kaur, P. (2018). Enhanced Approach Of Using Custom Heuristic Rules With Stanford And Naive Bayes Classification Technique. 2018 International Conference On Advances In Communication And Computing Technology (Icacct), 601–605.

Madasu, A. (2019). A Study Of Feature Extraction Techniques For Sentiment Analysis. Arxiv Preprint Arxiv:1906.01573.

Manning, C. D. (2008). Introduction To Information Retrieval. Syngress Publishing.

Meidina, S. C. M. S. C. (2025). Akuntabilitas Pemerintah Daerah Dalam Penanggulangan Bencana Hidrometeorologi Di Sumatera. Equality Before The Law, 5(2).

Munawar, M., Sartika, D., & Husnah, F. (2025). Lexicon-Based Comparison For Suicide Sentiment Analysis On Twitter (X). Telkomnika (Telecommunication Computing Electronics And Control), 23(5), 1314–1322.

Nyoto, V. J., Riti, Y. F., & Tantokusumo, R. V. P. (2026). Analisis Perbandingan Algoritma Random Forest, Decision Tree Dan Naive Bayes Dalam Mendeteksi Spam Sms. Jurnal Sains Informatika Terapan, 5(1), 279–286.

Prasetyo, V. R., Erlangga, G., & Prima, D. A. (2023). Analisis Sentimen Untuk Identifikasi Bantuan Korban Bencana Alam Berdasarkan Data Di Twitter Menggunakan Metode Kmeans Dan Naïve Bayes. Jurnal Teknologi Informasi Dan Ilmu Komputer (Jtiik), 10(5), 1055–1062.

Ramadani, N. C. (2024). Analisis Sentimen Untuk Mengukur Ulasan Pengguna Aplikasi Mobile Legend Menggunakan Algoritma Naive Bayes, Svm, Random Fores, Decision Tree, Dan Logistic Regression. J. Sist. Inf, 16(1), 123–138.

Safitri, R., Alfira, N., Tamitiadini, D., Dewi, W. W. A., & Febriani, N. (2021). Analisis Sentimen: Metode Alternatif Penelitian Big Data. Universitas Brawijaya Press.

Salsa, A. (2025). Analisis Sentimen Tentang Respon Masyarakat Terhadap Pelayanan Digital Administrasi Pertanahan (Studi: Di Kantor Wilayah Badan Pertanahan Nasional Provinsi Lampung).

Saputra, J., Maryani, L., Wulandari, D., & Eka, W. (2025). Analisis Performa Naive Bayes Dan Svm Terhadap Sentimen Teks Media Sosial Dengan Word2vec Dan Smote. Jurnal Instek (Informatika Sains Dan Teknologi), 10(1), 143–155.

Sari, A., Irawan, B., Faqih, A., Dikananda, A. R., & Fathurrohman, F. (2025). Analisis Sentimen Ulasan Pengguna Aplikasi Kredivo Menggunakan Algoritma Support Vector Machine (Svm) Dengan Metode Tf–Idf. Linier: Literatur Informatika Dan Komputer, 2(4), 593–601.

Ulya, D. M. (2026). Evaluasi Kinerja Algoritma Regresi Logistik Menggunakan Oversampling Smote Untuk Analisis Sentimen Ulasan Pengguna Aplikasi Mobile Jkn. Universitas Islam Negeri Maulana Malik Ibrahim.