Analisis Sentimen Opini Publik Terhadap Kebijakan Pemerintah Tentang Penetapan Bencana Nasional Sumatera Aceh Menggunakan Algoritma Naïve Bayes
DOI:
https://doi.org/10.47065/bulletincsr.v6i5.1224Keywords:
Sentiment Analysis; Public Opinion; Government Policy; Aceh National Disaster; Machine Learning; Confusion Matrix; ROC CurveAbstract
This study aims to analyze public opinion sentiment toward the Indonesian government’s policy on the designation of Aceh as a National Disaster by utilizing machine learning techniques on online review data. Sentiment labeling was conducted automatically based on user rating scores, where ratings of 1–2 were classified as negative, rating 3 as neutral, and ratings of 4–5 as positive. The labeling results indicate that the dataset is dominated by negative sentiment with 5,593 reviews, followed by 1,956 neutral reviews and 1,460 positive reviews, reflecting the prevalence of critical public responses to the policy. Model performance was evaluated using cross-validation, confusion matrix analysis, and the Receiver Operating Characteristic (ROC) curve. The cross-validation results show an average accuracy of 80.62% with a low standard deviation, indicating stable and consistent model performance. The confusion matrix analysis reveals that the model performs very well in classifying negative sentiment, but still faces challenges in distinguishing neutral and positive sentiments due to linguistic ambiguity and overlapping contextual expressions. Furthermore, the ROC curve evaluation demonstrates good discriminative ability, with AUC values of 0.84 for the negative class and 0.82 for both neutral and positive classes. Overall, the results indicate that the proposed sentiment analysis model is effective in capturing public opinion patterns regarding the National Disaster designation policy in Aceh, although further improvements are required to enhance contextual understanding, particularly for neutral and positive sentiments.
Downloads
References
Y. Yadi, “Analisa Usability Pada Website Traveloka,” Jurnal Ilmiah Betrik, vol. 9, no. 03, pp. 172–180, 2018, doi: 10.36050/betrik.v9i03.43.
M. Y. Hidayat, “Analisis Sentimen Terhadap Pidato Presiden 2026 Pada Aplikasi Tiktok dan X Menggunakan Metode Naive Bayes Classifier,” SAINTEKES: Jurnal Sains, Teknologi dan Kesehatan, vol. 5, no. 1, pp. 15–23, 2026, doi: 10.55681/saintekes.v1i1.xxx.
I. W. A. Agetia, N. L. E. Armoni, and I. P. A. U. Irawan, “Evaluasi Kinerja Algoritma Naïve Bayes, SVM, dan IndoBERT pada Analisis Sentimen Ulasan Pengguna Gojek Berbasis Text Mining,” TIN: Terapan Informatika Nusantara, vol. 7, no. 1, pp. 89–98, 2026, doi: 10.47065/tin.v7i1.9617.
R. P. Sundawa, M. R. Zahran, and B. Irfansyah, “Perbandingan Metode Naïve Bayes dan Support Vector Machine untuk Analisis Sentimen pada Ulasan Pengguna Aplikasi Roblox,” Jurnal Teknik Informatika dan Teknologi Informasi, vol. 6, no. 1, pp. 100–115, 2026, doi: 10.55606/jutiti.v6i1.6569.
F. Rahutomo, I. Y. R. Pratiwi, and D. M. Ramadhani, “Eksperimen Naïve Bayes Pada Deteksi Berita Hoax Berbahasa Indonesia,” Jurnal Penelitian Komunikasi Dan Opini Publik, vol. 23, no. 1, 2019, doi: 10.33299/jpkop.23.1.1805.
I. Elly, “Klasifikasi Text Mining Review Produk Kosmetik Untuk Teks Bahasa Indonesia Menggunakan Algoritma Naive Bayes,” Jurnal Khatulistiwa Informatika, vol. VII, no. 1, pp. 29–36, 2019, doi: 10.31294/jki.v7i1.5740.
P. M. Nirmala Dharmapatni and N. L. P. Merawati, “Penerapan Algoritma Support Vector Machine Dalam Sentimen Analisis Terkait Kenaikan Tarif BPJS Kesehatan,” Jurnal Bumigora Information Technology (BITe), vol. 2, no. 2, pp. 105–112, 2020, doi: 10.30812/bite.v2i2.904.
D. A. Faroek, M. Yusuf, and G. Syatauw, “Analisis Sentimen Terhadap Popularitas Partai Pendukung Capres 2024 di Twitter Menggunakan Algoritma Naive Bayes Classifier,” Antivirus?: Jurnal Ilmiah Teknik Informatika, vol. 17, no. 2, pp. 216–226, 2024, doi: 10.35457/antivirus.v17i2.3261 216.
F. Nurhuda, S. Widya Sihwi, and A. Doewes, “Analisis Sentimen Masyarakat terhadap Calon Presiden Indonesia 2014 berdasarkan Opini dari Twitter Menggunakan Metode Naive Bayes Classifier,” Jurnal Teknologi & Informasi ITSmart, vol. 2, no. 2, p. 35, 2016, doi: 10.20961/its.v2i2.630.
L. Lingga and F. N. Hasan, “Penerapan Naïve Bayes untuk Mengklasifikasikan Sentimen Tidak Seimbang pada Ulasan Aplikasi Berbasis Etika Konsumen,” Journal of Information System Research (JOSH), vol. 6, no. 4, pp. 2294–2306, 2025, doi: 10.47065/josh.v6i4.7867.
M. Ikbal, S. Andryana, and R. T. Komala Sari, “Visualisasi dan Analisa Data Penyebaran Covid-19 dengan Metode Klasifikasi Naïve Bayes,” Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi), vol. 5, no. 4, pp. 389–394, 2021, doi: 10.35870/jtik.v5i4.233.
F. M. Nizam, D. I. Sudahri, and E. Irawan, “Penerapan Metode Naive Bayes Dalam Menentukan Tingkat Kenyamanan Pada Rumah Sakit Terhadap Pasien,” KLIK: Kajian Ilmiah Informatika dan Komputer, vol. 2, no. 3, pp. 117–122, 2021, doi: 10.30865/klik.v2i3.297.
F. A. Nugroho, A. F. Solikin, M. D. Anggraini, and K. Kusrini, “Sistem Pakar Diagnosa Virus Corona Dengan Metode Naïve Bayes,” Jurnal Teknologi Informasi dan Komunikasi (TIKomSiN), vol. 9, no. 1, p. 81, 2021, doi: 10.30646/tikomsin.v9i1.553.
A. F. Watratan, A. P. B, and D. Moeis, “Implementation of the Naive Bayes Algorithm to Predict the Spread of Covid-19 in Indonesia,” Journal of Applied Computer Science and Technology, vol. 1, no. 1, pp. 7–14, 2020, doi: 10.55606/jurritek.v1i1.127.
P. S. M. Suryani, L. Linawati, and K. O. Saputra, “Penggunaan Metode Naïve Bayes Classifier pada Analisis Sentimen Facebook Berbahasa Indonesia,” Majalah Ilmiah Teknologi Elektro, vol. 18, no. 1, p. 145, 2019, doi: 10.24843/mite.2019.v18i01.p22.
S. Rahayu, Y. MZ, J. E. Bororing, and R. Hadiyat, “Implementasi Metode K-Nearest Neighbor (K-NN) untuk Analisis Sentimen Kepuasan Pengguna Aplikasi Teknologi Finansial FLIP,” Edumatic: Jurnal Pendidikan Informatika, vol. 6, no. 1, pp. 98–106, 2022, doi: 10.29408/edumatic.v6i1.5433.
R. T. Atmi, “Evaluation of The Library and Archives of East Java’s Workshop as A Knowledge Sharing Form of Jawatimuran Local Wisdom Preservation,” Record and Library Journal, vol. 1, no. 2, p. 172, 2016, doi: 10.20473/rlj.v1i2.1171.
F. David, “Visualisasi Data Dalam Bentuk 3 Dimensi Dengan Abstrak Seminar Nasional PIMIMD-5 , ITP , Padang,” pp. 1–6, 2019, doi: 10.21063/PIMIMD5.2019.1.
M. Yoka Fathoni, S. Wijayanto, “Forecasting Penjualan Gas LPG di Toko Sembako Menggunakan Metode Fuzzy Time Series,” JUPITER (Jurnal Penelitian Ilmu dan Teknologi Komputer), vol. 13, no. 2, pp. 87–96, 2021, doi: 10.5281/3541.jupiter.2021.10
R. N. Irawan, K. M. Hindrayani, “Penerapan Cross Validation sebagai Analisis Sentimen Pelayanan Publik Kereta Api Lokal Daop 8 Menggunakan Metode Multinomial Naïve Bayes,” G-Tech?: Jurnal Teknologi Terapan, vol. 6, no. 2, pp. 295–305, 2022, doi: 10.33379/gtech.v8i2.4117.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Analisis Sentimen Opini Publik Terhadap Kebijakan Pemerintah Tentang Penetapan Bencana Nasional Sumatera Aceh Menggunakan Algoritma Naïve Bayes
ARTICLE HISTORY
How to Cite
Issue
Section
Copyright (c) 2026 Ghivarel Ghivarel, Joni Karman, Satrianansyah Satrianansyah
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
