Comparison of Naive Bayes and Support Vector Machine Algorithms in Sentiment Analysis

Tiara Sela(1*),Anisya Sonita(2)
(1) Universitas Muhammadiyah Bengkulu
(2) Universitas Muhammadiyah Bengkulu
(*) Corresponding Author
DOI : 10.35889/jutisi.v14i2.2727

Abstract

Twitter is a social media platform that quickly spreads public opinion. The Ronald Tannur case, widely discussed on this platform, triggered various public reactions. This study aims to compare the Naive Bayes and Support Vector Machine (SVM) algorithms in analyzing netizens’ sentiment toward the case. The process includes data collection and text preprocessing, such as removing duplicates, cleaning, case folding, word normalization, stopword removal, tokenization, and stemming. The text is then transformed using TF-IDF. Sentiment classification is performed using both algorithms and evaluated through metrics like accuracy, precision, recall, F1-score, and AUC. The models are tested on three data split schemes: 90:10, 80:20, and 70:30. The results show that SVM with 90% training data provides the best performance, achieving 88.78% accuracy and 0.84 AUC, outperforming Naive Bayes, which only reached 71.29% accuracy and 0.77 AUC. This shows that SVM is more accurate in detecting sentiment on social media.

Keywords : Sentiment Classification; Naive Bayes Algorithm; Support Vector Machine Algorithm; Twitter; Python

 

Abstrak

Twitter merupakan media sosial yang cepat menyebarkan opini publik. Kasus Ronald Tannur, yang banyak dibicarakan di platform ini, memicu beragam reaksi dari masyarakat. Penelitian ini bertujuan untuk membandingkan algoritma Naive Bayes dan Support Vector Machine (SVM) dalam menganalisis sentimen warganet terhadap kasus tersebut. Proses analisis mencakup pengumpulan data, praproses teks seperti penghapusan duplikat, pembersihan, case folding, normalisasi kata, penghapusan stopword, tokenisasi, dan stemming, lalu data ditransformasi menggunakan TF-IDF. Klasifikasi sentimen dilakukan menggunakan kedua algoritma dan dievaluasi dengan metrik seperti akurasi, presisi, recall, F1-score, dan AUC. Pengujian dilakukan pada tiga skema pembagian data latih dan uji, yaitu 90:10, 80:20, dan 70:30. Hasil menunjukkan bahwa SVM dengan rasio data latih 90% memberikan hasil terbaik dengan akurasi 88,78% dan AUC 0,84, melampaui Naive Bayes yang hanya mencapai akurasi 71,29% dan AUC 0,77. Ini menunjukkan bahwa SVM lebih akurat dalam mengenali sentimen di media sosial.

 

Keywords


Klasifikasi Sentimen; Algoritma Naive Bayes; Algoritma Support Vector Machine; Twitter; Python

References


S. Rabbani, D. Safitri, N. Rahmadhani, A. A. F. Sani, and M. K. Anam, “Perbandingan Evaluasi Kernel SVM untuk Klasifikasi Sentimen dalam Analisis Kenaikan Harga BBM,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 3, no. 2, pp. 153–160, 2023, doi: 10.57152/malcom.v3i2.897.

D. Oktavia, Y. R. Ramadahan, and Minarto, “Analisis Sentimen Terhadap Penerapan Sistem E-Tilang Pada Media Sosial Twitter Menggunakan Algoritma Support Vector Machine (SVM),” KLIK: Kajian Ilmiah Informatika dan Komputer, vol. 4, no. 1, pp. 407–417, 2023, doi: 10.30865/klik.v4i1.1040.

M. A. A, M. Alamsyah, and M. F. Arif, “Analisis Sentimen Twitter Tentang Pinjaman Online di Indonesia Menggunakan Metode Random Forest,” Jurnal Ilmiah Teknik Informatika dan Sistem Informasi, vol. 13, no. 2, pp. 1410–1421, 2024, doi: 10.35889/jutisi.v13i2.2215.

A. Asyer and M. A. I. Pakereng, “Analisis Sentimen Tweet Pengguna Twitter Terkait Diabetes Menggunakan Metode Naive Bayes,” Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi, vol. 12, no. 2, pp. 627–636, 2023, doi: 10.35889/jutisi.v12i2.1234.

A. F. Setyaningsih, D. Septiyani, and S. R. Widiasari, “Implementasi Algoritma Naïve Bayes untuk Analisis Sentimen Masyarakat pada Twitter mengenai Kepopuleran Produk Skincare di Indonesia,” Jurnal Teknlogi Informatika dan Komputer MH. Thamrin, vol. 9, no. 1, pp. 224–235, 2023, doi: 10.37012/jtik.v9i1.1409.

R. Rachman and R. N. Handayani, “Klasifikasi Algoritma Naive Bayes Dalam Memprediksi Tingkat Kelancaran Pembayaran Sewa Teras UMKM,” Jurnal Informatika, vol. 8, no. 2, pp. 111–122, 2021, doi: 10.31294/ji.v8i2.10494.

Putri Ramayanti and Tata Sutabri, “Perbandingan Algoritma Naïve Bayes Dan Svm Untuk Analisis Penyalahgunaan Kejahatan Carding,” Jurnal Informatika Teknologi dan Sains, vol. 5, no. 1, pp. 18–24, 2023, doi: 10.51401/jinteks.v5i1.2231.

R. I. Agustin, “Komparasi Algoritma Naïve Bayes Dan Svm Untuk Analisis Sentimen Twitter Korupsi Bansos Beras Masa Pandemi,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 2, pp. 912–918, 2024, doi: 10.23960/jitet.v12i2.4020.

S. D. Fitri, “Jurnal Sistem dan Teknologi Informasi Indonesia Perbandingan Metode Naïve Bayes dan Support Vector Machine Pada Kasus Pembunuhan Vina Cirebon Berdasarkan Data X Comparison of Naïve Bayes and Support Vector Machine Methods in the Vina Cirebon Murder Case B,” Jurnal Sistem dan Teknologi Informasi Indonesia, vol. 10, no. 1, pp. 39–49, 2025, doi: 10.32528/justindo.v10i1.2550.

U. R. Debora, I. P. A. E. Pratama, and G. M. A. Sasmita, “Sentiment Analysis of Domestic Violence Issues on Twitter Using Multinomial Naïve Bayes and Support Vector Machine,” JITTER : Jurnal Ilmiah Teknologi dan Komputer, vol. 4, no. 3, p. 1992, 2024, doi: 10.24843/jtrti.2023.v04.i03.p06.

Septi Putri, Yohanes Agung Apriyanto, and Andri Wijaya, “Analisis Sentimen Ulasan Aplikasi Deepl Pada Google Play Dengan Metode Support Vector Machine (Svm),” Jurnal Sistem Informasi (JUSIN), vol. 4, no. 2, pp. 59–66, 2023, doi: 10.32546/jusin.v4i2.2368.

C. Muhamad, S. Ramdani, A. N. Rachman, and R. Setiawan, “Comparison of the Multinomial Naive Bayes Algorithm and Decision Tree with the Application of AdaBoost in Sentiment Analysis Reviews PeduliLindungi Application,” International Journal of Information System & Technology Akreditasi, vol. 6, no. 158, pp. 419–430, 2022, doi: 10.30645/ijistech.v6i4.257.

J. C. Moris Dachi Sunneng Sandino Berutu2, “Klasifikasi Sentimen Opini Pada Aplikasi Guitar Tuner,” Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi, vol. 13, no. 2, pp. 1444–1459, 2024, doi: 10.35889/jutisi.v13i2.2041.

A. Muzaki and A. Witanti, “Sentiment Analysis of the Community in the Twitter To the 2020 Election in Pandemic Covid-19 By Method Naive Bayes Classifier,” Jurnal Teknik Informatika (Jutif), vol. 2, no. 2, pp. 101–107, 2021, doi: 10.20884/1.jutif.2021.2.2.51.

B. A. Maulana, M. J. Fahmi, A. M. Imran, and N. Hidayati, “Analisis Sentimen Terhadap Aplikasi Pluang Menggunakan Algoritma Naive Bayes dan Support Vector Machine (SVM),” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 4, no. 2, pp. 375–384, 2024, doi: 10.57152/malcom.v4i2.1206.

F. Matheos Sarimole and K. Kudrat, “Analisis Sentimen Terhadap Aplikasi Satu Sehat Pada Twitter Menggunakan Algoritma Naive Bayes Dan Support Vector Machine,” Jurnal Sains dan Teknologi, vol. 5, no. 3, pp. 783–790, 2024, doi: 10.55338/saintek.v5i3.2702.


The PDF file you selected should load here if your Web browser has a PDF reader plug-in installed (for example, a recent version of Adobe Acrobat Reader).

If you would like more information about how to print, save, and work with PDFs, Highwire Press provides a helpful Frequently Asked Questions about PDFs.

Alternatively, you can download the PDF file directly to your computer, from where it can be opened using a PDF reader. To download the PDF, click the Download link above.

Fullscreen Fullscreen Off

Full Text: File PDF

How To Cite This :

Refbacks

  • There are currently no refbacks.