Performance Comparison of Naïve Bayes and SVM Methods in Sentiment Analysis of Twitter/X Users Toward Sidoarjo Regency PDAM Service Quality
Perbandingan Kinerja Metode Naïve Bayes dan SVM dalam Analisis Sentimen Pengguna Twitter/X terhadap Kualitas Pelayanan PDAM Kabupaten Sidoarjo
DOI:
https://doi.org/10.21070/ups.11521Keywords:
PDAM, Naïve Bayes, SVM, Sentiment Analysis, Twitter, Public Services, Data TwitterAbstract
The widespread use of X (Twitter) has made it an important platform for expressing public opinions on public services, including PDAM. This study compares the performance of Naïve Bayes and Support Vector Machine (SVM) in classifying public sentiment toward the service quality of PDAM Sidoarjo Regency. A total of 4,339 valid tweets (571 positive, 1,706 negative, and 2,062 neutral) were collected through web scraping. The data were preprocessed, balanced using the Synthetic Minority Over-sampling Technique (SMOTE) on the training set, and transformed using Term Frequency–Inverse Document Frequency (TF-IDF). Four SVM kernels and four Naïve Bayes variants were evaluated under three train–test split scenarios. The results show that SVM consistently outperformed Naïve Bayes. SVM RBF achieved the highest accuracy (75.35%), while SVM Linear obtained the highest F1-score (74.23%), demonstrating that SVM is more effective for multi-class sentiment classification of PDAM service quality.
References
A. Septiana et al., “Dalam Analisis Sentimen Pengguna Twitter X Terhadap,” vol. 8, no. 1, pp. 323–330, 2024.
F. F. Mailoa, “Analisis sentimen data twitter menggunakan metode text mining tentang masalah obesitas di indonesia,” J. Inf. Syst. Public Heal., vol. 6, no. 1, p. 44, 2021, doi: 10.22146/jisph.44455.
P. Covid- and M. A. Pono, “Persepsi Masyarakat Terhadap aktivitas Publikasi Perumda air Minum Kota Makassar Dalam Menangani Keluhan Pelanggan Dimasa,” pp. 78–89.
H. Zahra, S. Santoso, and I. A. Kurniawan, “Penerapan sistem informasi pelayanan publik pada aplikasi simpel tkr pdam tirta kerta raharja kabupaten tangerang,” vol. 7, no. September, pp. 87–98, 2024.
F. Ali, A. Setiawan, R. Nuraini, and S. Fathonah, “TINJAUAN SISTEMATIS LITERATUR : ANALISIS SENTIMEN TERHADAP,” vol. 9, no. 5, pp. 7995–8003, 2025.
F. M. Sarimole, “Analisis Sentimen Terhadap Aplikasi Satu Sehat Pada Twitter Menggunakan Algoritma Naive Bayes Dan Support Vector Machine,” vol. 5, no. 3, pp. 783–790, 2024.
R. Mursyid, A. D. Indriyanti, J. Teknik, I. Fakultas, T. Universitas, and N. Surabaya, “Perbandingan Akurasi Metode Analisis Sentimen Untuk Evaluasi Opini Pengguna Pada Platform Media Sosial ( Studi Kasus : Twitter ),” vol. 06, pp. 371–383, 2024.
M. Difanada, H. Setiawan, and I. A. Kautsar, “Penerapan metode support vector machine (svm) untuk memprediksi pemilihan karir bagi alumni umsida,” vol. 10, no. 4, pp. 2906–2916, 2025.
J. R. Informasi et al., “ANALISIS KOMPREHENSIF KINERJA MODEL KLASIFIKASI SENTIMEN : EVALUASI LINTAS METRIK PADA DATASET TWEET FILM BAHASA,” vol. 14, no. 1, 2025.
L. A. Qomariah et al., “KLASIFIKASI SENTIMEN ULASAN MINECRAFT PADA GOOGLE PLAY STORE : STUDI KOMPARATIF NAÏVE BAYES DAN RANDOM FOREST,” vol. 10, no. 1, pp. 1227–1234, 2026.
A. Rahman and H. Suroyo, “Analisis Data Produk Elektronik Di E-Commerce Dengan Metode Algoritma K-Means Menggunakan Python,” vol. 3, no. 2, pp. 11–18, 2021.
Y. Asri, W. N. Suliyanti, D. Kuswardani, and M. Fajri, “Pelabelan Otomatis Lexicon Vader dan Klasifikasi Naive Bayes dalam menganalisis sentimen data ulasan PLN Mobile,” vol. 15, no. 2, pp. 264–275, 2022.
U. Khairani et al., “PENGARUH TAHAPAN PREPROCESSING TERHADAP MODEL INDOBERT DAN THE INFLUENCE OF PREPROCESSING STAGES ON INDOBERT AND INDOBERTWEET MODELS FOR EMOTION DETECTION IN INSTAGRAM NEWS,” vol. 11, no. 4, 2024, doi: 10.25126/jtiik.1148315.
A. Firizkiansah, A. Muhammad, I. R. Maulana, U. S. Indonesia, and K. Bekasi, “Optimasi Klasifikasi Data Teks Menggunakan Algoritma Logistic Regression dengan TF-IDF dan SMOTE,” vol. 2, no. 1, pp. 29–36, 2025.
M. Sulistiyono et al., “Implementasi Algoritma Synthetic Minority Over - Sampling Technique untuk Menangani Ketidakseimbangan Kelas pada Dataset Klasifikasi,” vol. 10, pp. 445–459, 2021.
E. Martantoh, N. Yanih, T. Informatika, U. Panca, and S. Bekasi, “Implementasi Metode Naïve Bayes Untuk Klasifikasi Karakteristik Kepribadiaan Siswa Di Sekolah MTS Darussa ’ adah Menggunakan PHP MySQL,” vol. 3, no. 2, pp. 166–175, 2022.
D. R. Nurqotimah, A. N. Khudori, and R. S. Pradini, “JOURNAL OF APPLIED COMPUTER SCIENCE AND TECHNOLOGY ( JACOST ) Implementasi Algoritma Support Vector Machine ( SVM ) Untuk Klasifikasi Penyakit Stroke,” vol. 5, no. 2, pp. 179–185, 2024.
Downloads
Additional Files
Posted
License
Copyright (c) 2026 UMSIDA Preprints Server
This work is licensed under a Creative Commons Attribution 4.0 International License.
