Comparison of IndoBERT and Naive Bayes Performance on Sentiment Analysis of Indonesian-Language E-Commerce Reviews
DOI:
https://doi.org/10.61536/ambidextrous.v5i02.648Keywords:
Sentiment Analysis, IndoBERT, Naive Bayes, E-Commerce, Natural Language ProcessingAbstract
The growth of e-commerce platforms in Indonesia has generated a large number of user reviews containing important information about service quality and user satisfaction. Manual analysis of these reviews is inefficient, necessitating a Natural Language Processing (NLP)-based approach. This study aims to compare the performance of Naive Bayes and IndoBERT in sentiment classification of Indonesian-language e-commerce reviews. The dataset consists of 26,103 reviews of Tokopedia, Shopee, and Lazada apps obtained from the Google Play Store. The research stages include sentiment labeling based on ratings, preprocessing, Term Frequency–Inverse Document Frequency (TF-IDF) weighting on Naive Bayes, fine-tuning IndoBERT, and evaluation using a confusion matrix with accuracy, precision, recall, and F1-score metrics. The results show that Naive Bayes achieved an accuracy of 80.53%, while IndoBERT achieved 86.48% with a Macro F1-Score of 0.6515 and a Weighted F1-Score of 0.8723. These results show that IndoBERT is more effective in understanding the context of Indonesian text, resulting in better sentiment classification performance.
Downloads
References
A. Mao et, “Journal of King Saud University - Computer and Sentiment analysis methods, applications, and challenges : A systematic literature review,” J. King Saud Univ. - Comput. Inf. Sci., vol. 36, no. 4, p. 102048, 2024, doi: 10.1016/j.jksuci.2024.102048.
A. Hermawan and I. Jowensen, “Implementation of Text-Mining for Sentiment Analysis on Twitter with Support Vector Machine Algorithm,” vol. 12, no. 1, pp. 129–137, 2023.
F. Romadoni, Y. Umaidah, and BN Sari, “Text Mining for Customer Sentiment Analysis of Electronic Money Services Using Support Vector Machine Algorithm,” vol. 09, pp. 247–253, 2020.
A. Nurian, BN Sari, US Karawang, and T. Timur, “Sentiment analysis of Google Play app user reviews using naive Bayes,” vol. 11, no. 3, pp. 829–835, 2023.
Agus Hermanto, “IMPLEMENTATION OF TEXT MINING USING NAIVE BAYES TO DETERMINE STUDENTS’ FINAL ASSIGNMENT CATEGORIES BASED ON THEIR ABSTRACT,” vol. 12, pp. 1–10, 2021.
Tania Puspa Rahayu Sanjaya, Ahmad Fauzi, and Anis Fitri Nur Masruriyah, “Sentiment analysis of reviews on e-commerce shopee using naive bayes algorithm and support vector machine,” INFOTECH J. Inform. Teknol., vol. 4, no. 1, pp. 16–26, 2023, doi: 10.37373/infotech.v4i1.422.
A. Kesumawati and AK Talib, "Hoax Classification with Term Frequency - Inverse Document Frequency Using Non-Linear SVM and Naïve Bayes," vol. 10, no. 3, 2023.
Devlin, M. C. Kenton, and L. Kristina, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” no. MLM, 2020.
K. Mohiuddin et al., “Retention Is All You Need,” Int. Conf. Inf. Knowl. Manag. Proc., no. Nips, pp. 4752–4758, 2023, doi: 10.1145/3583780.3615497.
B. Wilie et al., “IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding,” Proc. 1st Conf. Asia-Pacific Chapter Assoc. Comput. Linguist. 10th Int. Jt. Conf. Nat. Lang. Process. AACL-IJCNLP 2020, pp. 843–857, 2020, doi: 10.18653/v1/2020.aacl-main.85.
H. Jayadianti, W. Kaswidjanti, A.T. Utomo, S. Saifullah, F.A. Dwiyanto, and R. Drezewski, “Sentiment analysis of Indonesian reviews using fine-tuning IndoBERT and R-CNN,” Ilk. J. Ilm., vol. 14, no. 3, pp. 348–354, 2022, doi: 10.33096/ilkom.v14i3.1505.348-354.
DK Sumartha, “Public Opinion on the UKT Increase Policy in the Era of Government,” vol. 13, no. 3, 2025.
P. Maxmiliano, YF Riti, IY Nugroho, and CEC Juniarto, “Comparison of Naive Bayes and BERT Algorithms for Sentiment Analysis of Shopee Product Reviews Based on Ratings and Product Attributes (Color/Category),” J. Media Inform., vol. 6, no. 5, pp. 2552–2565, 2025.
RF Kireyna Cindy Pradhisa, “Sentiment Analysis of E-commerce User Reviews on Google Play Store Using the IndoBERT Method,” 2024.
A. Putra, A., Ismarmiaty, “Measuring the Level of Accuracy in E-Commerce Reviews Using the INDOBERT Method with Adam Optimizer,” J. Komputer, Inf. dan Teknol., vol. 5, no. 1, pp. 1–15, 2025.
M. Adi Widianto, Eka Pebriyanto, Fitriyanti, "Document Similarity using Term Frequency-Inverse Document Frequency Representation and Cosine Similarity," vol. 4, no. 2, pp. 149–153, 2024.
S. Hidayati, A. Nuraini, and F. Rahayu, “Designing a Posyandu nutrition education application for stunting prevention,” J. Abdika, vol. 6, no. 2, pp. 122–129, 2022, [Online]. Available: https://uniflor.ac.id/e-journal/index.php/abdika/article/view/3435
V. As. Np. Nu. Jj. Lg. Ak. Łp. I, “Attention Is All You Need,” no. Nips, 2020.
T. Baldwin, “IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP,” 2020.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Tony Kurniawan, Soffa Zahara, Yanuarini Nur Sukmaningtyas
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
