Analisis Perbandingan Algoritma SVM, Naïve Bayes, dan Perceptron untuk Analisis Sentimen Ulasan Produk Tokopedia

Authors

  • Muhammad Aulia Universitas Teknologi Yogyakarta, Yogyakarta
  • Arief Hermawan Universitas Teknologi Yogyakarta, Yogyakarta

DOI:

https://doi.org/10.30865/mib.v7i4.6839

Keywords:

Perceptron, Multinomial Naïve Bayes, Support Vector Machine, Tokopedia, Sentiment Analysis

Abstract

The rapid growth of the online market in Indonesia has changed the business landscape. Tokopedia, one of the leading E-commerce platforms, serves millions of users with a variety of products. In the fierce E-commerce competition, understanding customer reviews is very important. However, performing review analysis manually is a complex and time-consuming task. Sentiment analysis is needed to understand customer preferences, improve service quality, and maintain Tokopedia's competitiveness in the competitive E-commerce market. This study carried out a comparison between three algorithms, Support Vector Machine, Perceptron, and Multinomial Naïve Bayes to evaluate and determine the most effective and accurate algorithm in conducting sentiment analysis of product reviews on Tokopedia. The results of research using 2000 Tokopedia product review data show that Multinomial Naïve Bayes has the highest level of accuracy, reaching 84.00% and precision of 96.00%. Support Vector Machines has an accuracy rate of 80.00% and a precision value of 95.00%. Meanwhile, Perceptron provides 81.00% accuracy and 95.00% precision. Evaluation using the confusion matrix also indicates that Multinomial Naïve Bayes provides superior results with a truth level of 1011 for positive sentiment labels and 860 for negative sentiment labels. This research provides valuable insights regarding sentiment analysis of product reviews on Tokopedia, and the results can be a reference for further research exploring more innovative sentiment analysis methods or the application of technology to increase the efficiency of sentiment analysis in the context of E-commerce.

References

R. Maulana et al., “KOMPARASI ALGORITMA NAIVE BAYES DAN K-NEAREST NEIGHBOR PADA ANALISIS SENTIMEN TERHADAP ULASAN PENGGUNA APLIKASI TOKOPEDIA,†Jurnal Teknologi Informasi, vol. 17, no. 2, pp. 177–189, 2023, doi: 10.47111/JTI.

A. Tazidan OctaN et al., “ALGORITMA DECISION TREE UNTUK ANALISIS SENTIMEN PUBLIC TERHADAP MARKETPLACE DI INDONESIA,†Jurnal Ilmiah Nasional Riset Aplikasi dan Teknik Informatika (NARATIF), vol. 05, 2023.

A. Safira, A. S. Masyarakat…ï®, and F. N. Hasan, “ANALISIS SENTIMEN MASYARAKAT TERHADAP PAYLATER MENGGUNAKAN METODE NAIVE BAYES CLASSIFIER,†Jurnal Sistem Informasi, vol. 5, no. 1, 2023.

Irvandi, B. Irawan, and O. Nurdiawan, “NAIVE BAYES DAN WORDCLOUD UNTUK ANALISIS SENTIMEN WISATA HALAL PULAU LOMBOK,†INFOTECH journal, vol. 9, no. 1, pp. 236–242, May 2023, doi: 10.31949/infotech.v9i1.5322.

N. Kahar and W. Aritonang, “IMPLEMENTASI JARINGAN SYARAF TIRUAN DENGAN ALGORITMA PERCEPTRON DALAM PENENTUAN PROGRAM STUDI MAHASISWA BARU,†JURNAL AKADEMIKA, pp. 74–80, 2022.

E. Suryati, A. Ari Aldino, N. Penulis Korespondensi, and E. Suryati Submitted, “Analisis Sentimen Transportasi Online Menggunakan Ekstraksi Fitur Model Word2vec Text Embedding Dan Algoritma Support Vector Machine (SVM),†JURNAL TEKNOLOGI DAN SISTEM INFORMASI, vol. 4, no. 1, pp. 96–106, 2023, doi: 10.33365/jtsi.v4i1.2445.

A. Wibisono Informatika, “FILTERING SPAM EMAIL MENGGUNAKAN METODE NAIVE BAYES,†Teknologipintar.org, vol. 3, no. 4, pp. 1–22, 2023.

G. Ditami, E. Ripanti, and H. Sujaini, “Implementasi Support Vector Machineuntuk Analisis Sentimen Terhadap Pengaruh Program Promosi EventBelanja pada Marketplace,†JEPIN (Jurnal Edukasi dan Penelitian Informatika), vol. 8, no. 3, pp. 508–516, 2022.

A. Fauzi and Ginabila, “Analisis Sentimen Terhadap Pemutar Musik Online Spotify Dengan Algoritma Naive Bayes dan Support Vector Machine,†Jurnal Ilmiah ILKOMINFO - Jurnal Ilmu Komputer dan Informatika, pp. 2621–4962, 2023.

N. Ajijah and A. Kurniawan, “Klasifikasi Teks Mining Terhadap Analisa Isu Kegiatan Tenaga Lapangan Menggunakan Algoritma K-Nearest Neighbor (KNN),†, vol. 7, no. 1, 2023.

F. Kristanto, W. W. Winarno, and A. Nasiri, “Perbandingan Algoritme Naïve Bayes dan Decision Tree Pada Analisis Sentimen Data Komentar Siswa Pada Aplikasi Digital Teacher Assessment,†Jurnal Ilmiah Teknik Informatika dan Sistem Informais, pp. 538–548, 2023.

M. Zaki Anbari, M. Zaki Anbari, and B. Sugiantoro, “JURNAL MEDIA INFORMATIKA BUDIDARMA Studi Komparasi Metode Analisis Sentimen Naïve Bayes, SVM, dan Logistic Regression Pada Piala Dunia 2022,†JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 7, no. 2, pp. 688–695, 2023, doi: 10.30865/mib.v7i2.5383.

A. U. Nabiylah Ramadhanty and I. Najiyah, “IMPLEMENTASI WEB SCRAPING PADA SITUS JURNAL SINTA MENGGUNAKAN FRAMEWORKSELENIUM WEBDRIVER PYTHON,†JIKA (Jurnal Informatika), vol. 7, no. 1, pp. 29–36, 2023.

T. Maulana Fahrudin, P. Aji Riyantoko, K. Maulida Hindrayani, S. Data, F. Ilmu Komputer, and U. Pembangunan Nasional Veteran Jawa Timur, “Implementation of Web Scraping on Google Search Engine for Text Collection Into Structured 2D List,†Jurnal Informatika dan Teknologi Informasi, vol. 20, no. 2, pp. 139–152, 2023, doi: 10.31515/telematika.v20i2.9575.

M. L. Nugraha and E. B. Setiawan, “JURNAL MEDIA INFORMATIKA BUDIDARMA Bank Central Asia (BBCA) Stock Price Sentiment Analysis On Twitter Data Using Neural Convolutional Network (CNN) And Bidirectional Long Short-Term Memory (BI-LSTM),†JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 7, no. 3, 2023, doi: 10.30865/mib.v7i3.6120.

B. Bramantyo, M. Pajar, K. Putra, and N. Hendrastuty, “Implementasi Recurrent Neural Network Pada Multiclass Text Classification Judul Berita,†JURNAL MEDIA BORNEO, vol. 1, no. 1, 2023, doi: 10.58602/mediaborneo.v1i1.6.

N. Petty Wahyuningtyas, D. Eka Ratnawati, and N. Yudi Setiawan, “Root Cause Analysis (RCA) berbasis Sentimen menggunakan Metode K-Nearest Neighbor (K-NN) (Studi Kasus: Pengunjung Kolam Renang Brawijaya),†Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 7, no. 5, pp. 2515–2520, 2023, [Online]. Available: http://j-ptiik.ub.ac.id

S. Saepudin, S. Widiastuti, and C. Irawan, “Sentiment Analysis of Social Media Platform Reviews Using the Naïve Bayes Classifier Algorithm,†Jurnal Sisfokom (Sistem Informasi dan Komputer), vol. 12, no. 2, pp. 236–243, Jul. 2023, doi: 10.32736/sisfokom.v12i2.1650.

R. Nurlaely, D. Sartika Simatupang, and I. Lucia Kharisma, “Analisis Sentimen Twitter Terhadap Cyberbullying Menggunakan Metode Support Vector Machine (SVM),†Jurnal Computer Science and Information Technology(CoSciTech), vol. 4, no. 2, pp. 376–384, 2023, doi: 10.37859/coscitech.v4i2.5161.

A. Sinaga and S. P. Nainggolan, “Analisis Perbandingan Akurasi dan Waktu Proses Algoritma Stemming Arifin-Setiono dan Nazief-Adriani pada Dokumen Teks Bahasa Indonesia,†Jurnal SEBATIK, vol. 27, no. 1, p. 27, 2023, doi: 10.46984/sebatik.v27i1.2072.

R. B. Dahlian and D. Sitanggang, “Sentiment Analysis of Digital Television Migration on Twitter Using Naïve Bayes Multinomial Comparison, Support Vector Machines, and Logistic Regression Algorithms,†Jurnal Sisfokom (Sistem Informasi dan Komputer), vol. 12, no. 2, pp. 280–288, Jul. 2023, doi: 10.32736/sisfokom.v12i2.1668.

Downloads

Published

2023-10-24

Issue

Vol. 7 No. 4 (2023): Oktober 2023

Section

Articles

License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License

Authors who publish with this journal agree to the following terms:

  1. 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.
  2. 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.
  3. 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).