Implementasi Klasifikasi Sentimen Ulasan Produk Menggunakan Naive Bayes
Keywords:
e-commerce reviews, Naive Bayes, sentiment analysis, text classificationAbstract
The rapid growth of e-commerce platforms has generated a large volume of product reviews containing valuable information about customer opinions. Manually analyzing these reviews is inefficient and time-consuming, creating the need for automated sentiment classification. This study aims to implement the Naive Bayes algorithm to classify product review sentiments into positive and negative categories. The research method includes data collection from an e-commerce platform, text preprocessing (cleaning, tokenization, stopword removal, stemming, and TF-IDF weighting), data splitting into training and testing sets, model training, and performance evaluation using accuracy, precision, recall, and F1-score. The experimental results show that the proposed model achieved an accuracy of 0.87, precision of 0.85, recall of 0.83, and F1-score of 0.84, indicating good and balanced classification performance. The findings demonstrate that Naive Bayes is an effective and efficient approach for sentiment analysis of Indonesian product reviews. This study implies that simple probabilistic models can support business decision-making by providing automated insights into customer opinions.
Downloads
References
[1] A. Rahman, M. Iqbal, and S. Nurhayati, “Sentiment Analysis of E-Commerce Product Reviews Using Machine Learning Approach,” Journal of Big Data, vol. 8, no. 1, pp. 1–15, 2021.
[2] P. Kumar and R. Sharma, “Text Mining Techniques for Customer Review Analysis: A Review,” International Journal of Advanced Computer Science and Applications, vol. 12, no. 4, pp. 215–222, 2021.
[3] S. Li, L. Zhang, and H. Wang, “Recent Advances in Sentiment Analysis: A Survey,” IEEE Access, vol. 9, pp. 129–146, 2021.
[4] T. Prasetyo and D. Wahyuni, “Implementation of Sentiment Analysis on Marketplace Reviews Using Naive Bayes,” Journal of Information Systems Engineering and Business Intelligence, vol. 7, no. 2, pp. 95–102, 2021.
[5] R. Y. Putri, A. Fauzi, and M. A. Rizal, “Analisis Sentimen Ulasan Produk Berbahasa Indonesia Menggunakan Metode Naive Bayes,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 6, no. 1, pp. 45–52, 2022.
[6] M. K. Hasan and J. Uddin, “Performance Comparison of Machine Learning Algorithms for Text Classification,” Applied Artificial Intelligence, vol. 36, no. 1, pp. 1–18, 2022.
[7] N. Hidayat and R. Kurniawan, “Sentiment Classification on Indonesian Online Reviews Using TF-IDF and Naive Bayes,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 25, no. 3, pp. 1560–1567, 2022.
[8] L. Chen and Y. Xie, “A Comparative Study of Naive Bayes and Deep Learning for Text Sentiment Classification,” Expert Systems with Applications, vol. 197, pp. 116–128, 2022.
[9] F. Ramadhan, E. Utami, and S. Raharjo, “Optimasi Klasifikasi Sentimen Menggunakan Feature Selection dan Naive Bayes,” Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), vol. 10, no. 2, pp. 321–330, 2023.
[10] K. Singh and P. Arora, “Machine Learning-Based Sentiment Analysis: Recent Trends and Applications,” Information Processing & Management, vol. 60, no. 1, pp. 102–118, 2023.
[11] A. Saputra and B. Santoso, “Preprocessing Techniques in Indonesian Text Mining: Impact on Classification Accuracy,” Procedia Computer Science, vol. 216, pp. 350–357, 2023.
[12] Y. Zhang, Q. Liu, and J. Chen, “Feature Engineering for Text Classification: A Practical Review,” ACM Computing Surveys, vol. 56, no. 4, pp. 1–29, 2024.
[13] D. Purnama and L. Maharani, “Analisis Sentimen Marketplace Lokal Menggunakan Algoritma Naive Bayes,” Jurnal Nasional Teknologi dan Sistem Informasi, vol. 10, no. 1, pp. 12–20, 2024.
[14] H. Wang and X. Zhao, “Evaluation Metrics for Machine Learning Classification: A Systematic Review,” IEEE Access, vol. 12, pp. 45560–45575, 2024.
[15] M. Alqahtani and S. Alshahrani, “Efficient Sentiment Classification Using Probabilistic Models in E-Commerce Applications,” Future Internet, vol. 17, no. 2, pp. 1–14, 2025.
