Optimizing Sentiment Classification of E-Commerce Product Reviews: A Comparative Study of Naïve Bayes and SVM with SMO

Riki; Sonya Eliesse Dameria; Aditiya Hermawan; Junaedi; Yusuf Kurnia

doi:10.30595/juita.v13i3.26642

Authors

Riki Buddhi Dharma University
Sonya Eliesse Dameria Buddhi Dharma University
Aditiya Hermawan Buddhi Dharma University
Junaedi Buddhi Dharma University
Yusuf Kurnia Buddhi Dharma University

DOI:

https://doi.org/10.30595/juita.v13i3.26642

Keywords:

e-commerce, Naïve Bayes Classifier, review classification, Sequential Minimal Optimization (SMO), Support Vector Machine (SVM).

Abstract

The rapid growth of e-commerce has led to a surge in user-generated product reviews, making manual sentiment analysis impractical. This study explores automated sentiment classification using two machine learning algorithms: Naïve Bayes and Support Vector Machine (SVM) that is optimized with Sequential Minimal Optimization (SMO). The dataset comprises 2,000 Shopee product reviews that are labeled as positive, neutral, or negative. The study focuses on assessing the effectiveness of these algorithms in classifying product reviews, especially in the diverse and high-volume data that is typically on e-commerce environments. Empirical evaluation shows that Naïve Bayes achieves 68% accuracy, while SVM with SMO attains 79%. Additionally, the study evaluates other important performance metrics, such as precision, recall, and F1-score. This study show that SVM with SMO outperforms Naïve Bayes in accurately classifying product reviews. These findings highlight the superior capability of SVM with SMO in handling complex sentiment data, thereby offering a more robust foundation for automated review classification. This research provides insights into selecting suitable classifiers for improving customer experience and strategic decision-making in digital commerce.

References

[1] F. Tamimi and S. Munawaroh, “Teknologi Sebagai Kegiatan Manusia Dalam Era Modern Kehidupan Masyarakat,” Saturnus J. Teknol. dan Sist. Inf., vol. 2, no. 3, pp. 66–74, Jun. 2024, doi: 10.61132/saturnus.v2i3.157.

[2] A. Sacavém, A. de Bem Machado, J. R. dos Santos, A. Palma-Moreira, H. Belchior-Rocha, and M. Au-Yong-Oliveira, “Leading in the Digital Age: The Role of Leadership in Organizational Digital Transformation,” Adm. Sci., vol. 15, no. 2, pp. 1–21, 2025, doi: 10.3390/admsci15020043.

[3] N. Shaw, B. Eschenbrenner, and D. Baier, “Online shopping continuance after COVID-19: A comparison of Canada, Germany and the United States,” J. Retail. Consum. Serv., vol. 69, p. 103100, Nov. 2022, doi: 10.1016/j.jretconser.2022.103100.

[4] Y. N. Kusumawati and S. Indarto, “Challenges of Indonesian Industrialization and Trade Problems in the Industrial Era 4.0 for the Indonesian Economy and Government Policy Breakthrough,” Eduvest - J. Univers. Stud., vol. 4, no. 7, pp. 6037–6046, Jul. 2024, doi: 10.59188/eduvest.v4i7.1575.

[5] T. Sutarsih and K. Maharani, “Statistik Telekomunikasi Indonesia 2022,” Badan Pusat Statistik, 2022.

[6] C. B. Sivaparthipan, H. Alabdeli, P. Harshitha, Y. Nagendar, and G. G. Kulkarni, “An Optimization Model for Logistics Services in E-Commerce Market,” in 2024 Second International Conference on Data Science and Information System (ICDSIS), 2024, pp. 1–5, doi: 10.1109/ICDSIS61070.2024.10594347.

[7] C. V. Kalyan, V. V. S. N. Akhila Sree Rajeswari, Y. S. D. Phaneendra, and S. R. Kishan, “Lokart: Empowering Local Artisans through Mobile E-commerce,” in 2024 International Conference on Emerging Technologies in Computer Science for Interdisciplinary Applications (ICETCS), 2024, pp. 1–6, doi: 10.1109/ICETCS61022.2024.10543943.

[8] B. Marakarkandy, “Enhancing Multi-Channel Consumer Behavior Analysis: A Data-Driven Approach using the Optimized Apriori Algorithm,” J. Electr. Syst., vol. 20, no. 2s, pp. 700–708, 2024, doi: 10.52783/jes.1536.

[9] A. Prasetio, N. A. Witarsyah, and Indrawati, “The effect of e-WOM on purchase intention in e-commerce in Indonesia through the expansion of the information adoption model,” Int. J. Data Netw. Sci., vol. 8, no. 3, pp. 1959–1968, 2024, doi: 10.5267/j.ijdns.2024.1.017.

[10] H. Huang, A. A. Zavareh, and M. B. Mustafa, “Sentiment Analysis in E-Commerce Platforms: A Review of Current Techniques and Future Directions,” IEEE Access, vol. 11, pp. 90367–90382, 2023, doi: 10.1109/ACCESS.2023.3307308.

[11] X. Ma, Y. Li, and M. Asif, “E-Commerce Review Sentiment Analysis and Purchase Intention Prediction Based on Deep Learning Technology,” J. Organ. End User Comput., vol. 36, pp. 1–29, 2024, doi: 10.4018/JOEUC.335122.

[12] S. Gupta, P. S. Kushwaha, U. Badhera, P. Chatterjee, and E. D. R. S. Gonzalez, “Identification of benefits, challenges, and pathways in E-commerce industries: An integrated two-phase decision-making model,” Sustain. Oper. Comput., vol. 4, pp. 200–218, 2023, doi: 10.1016/j.susoc.2023.08.005.

[13] M. A. Salam and M. Ali, “Optimizing Extreme Learning Machine using GWO Algorithm for Sentiment Analysis,” Int. J. Comput. Appl., vol. 176, no. 38, pp. 22–28, 2020, doi: 10.5120/ijca2020920450.

[14] P. H. Prastyo, R. Hidayat, and I. Ardiyanto, “Enhancing sentiment classification performance using hybrid Query Expansion Ranking and Binary Particle Swarm Optimization with Adaptive Inertia Weights,” ICT Express, vol. 8, no. 2, pp. 189–197, Jun. 2022, doi: 10.1016/j.icte.2021.04.009.

[15] P. Kumar and Monika, “Improved Tweet Sentiment Analysis by Features Weight Optimize by GWO and Classify by XG-Boost,” 2023, pp. 607–614.

[16] Y. N. Kunang and W. P. Mentari, “Analysis of the Impact of Vectorization Methods on Machine Learning-Based Sentiment Analysis of Tweets Regarding Readiness for Offline Learning,” JUITA J. Inform., vol. 11, no. 2, p. 271, Nov. 2023, doi: 10.30595/juita.v11i2.17568.

[17] S. Riyadi, M. D. Mubarok, C. Damarjati, and A. J. Ishak, “Improving Sentiment Analysis Accuracy Using CRNN on Imbalanced Data: a Case Study of Indonesian National Football Coach,” JUITA J. Inform., vol. 12, no. 2, p. 159, Nov. 2024, doi: 10.30595/juita.v12i2.21847.

[18] V. R. Modhugu and S. Ponnusamy, “Comparative Analysis of Machine Learning Algorithms for Liver Disease Prediction: SVM, Logistic Regression, and Decision Tree,” Asian J. Res. Comput. Sci., vol. 17, pp. 188–201, May 2024, doi: 10.9734/ajrcos/2024/v17i6467.

[19] R. Guido, S. Ferrisi, D. Lofaro, and D. Conforti, “An Overview on the Advancements of Support Vector Machine Models in Healthcare Applications: A Review,” Inf., vol. 15, no. 4, 2024, doi: 10.3390/info15040235.

[20] H. Wang, G. Li, and Z. Wang, “Fast SVM classifier for large-scale classification problems,” Inf. Sci. (Ny)., vol. 642, p. 119136, Sep. 2023, doi: 10.1016/j.ins.2023.119136.

[21] Y. Wan, Z. Wang, and T.-Y. Lee, “Incorporating support vector machine with sequential minimal optimization to identify anticancer peptides,” BMC Bioinformatics, vol. 22, no. 1, p. 286, 2021, doi: 10.1186/s12859-021-03965-4.

[22] M. Madjid, D. Eka Ratnawati, and B. Rahayudi, “Sentiment Analysis on App Reviews Using Support Vector Machine and Naïve Bayes Classification,” Sinkron, vol. 8, pp. 556–562, Feb. 2023, doi: 10.33395/sinkron.v8i1.12161.

[23] A. Firdaus, A. Yudhana, and I. Riadi, “Prediction of Indonesian Presidential Election Results using Sentiment Analysis with Naïve Bayes Method,” J. MEDIA Inform. BUDIDARMA, vol. 8, pp. 41–50, Jan. 2024, doi: 10.30865/mib.v8i1.7007.

[24] F. Nurwanda, W. Sulandari, Y. Susanti, and Z. Reyhana, “Comparative Analysis Of Performance Levels Of Svm And Naïve Bayes Algorithm For Lifestyle Classification On Twitter Social Media,” Int. Conf. Digit. Adv. Tour. Manag. Technol., vol. 1, no. 1, pp. 215–230, 2023, doi: 10.56910/ictmt.v1i1.65.

[25] D. A. Putri, D. A. Kristiyanti, E. Indrayuni, A. Nurhadi, and D. R. Hadinata, “Comparison of Naive Bayes Algorithm and Support Vector Machine using PSO Feature Selection for Sentiment Analysis on E-Wallet Review,” J. Phys. Conf. Ser., vol. 1641, no. 1, 2020, doi: 10.1088/1742-6596/1641/1/012085.

[26] G. Novilia, R. Adriman, and T. F. Abidin, “Comparison of Classification Methods Using Feature Selection for Smartphone Sentiment Analysis,” in 2022 International Conference on Electrical Engineering, Computer and Information Technology (ICEECIT), 2022, pp. 44–48, doi: 10.1109/ICEECIT55908.2022.10030703.

[27] P. Pongthanoo and W. Songpan, “Feature Selection and Reduction Based on SMOTE and Information Gain for Sentiment Mining,” in 2020 5th International Conference on Computer and Communication Systems (ICCCS), 2020, pp. 109–114, doi: 10.1109/ICCCS49078.2020.9118467.

[28] H. Rahadian, A. Yudhana, and others, “Naive Bayes Method Monitoring Macro Nutrition and Soil Moisture Using Naive Bayes Method based on Internet of Things,” Bul. Ilm. Sarj. Tek. Elektro, vol. 5, no. 2, pp. 251–259, 2023, doi: 10.12928/biste.v5i2.6305.

[29] F. Ramadhani, A. Al-Khowarizmi, and I. Sari, Improving the Performance of Naïve Bayes Algorithm by Reducing the Attributes of Dataset Using Gain Ratio and Adaboost. 2021.

[30] H. Taherdoost, “Machine Learning Algorithms: Features and Applications,” 2022, pp. 938–960.

[31] H. Noviyanto and B. Mukti, “Period Study Accuracy Prediction using Sequential Minimal Optimization Algorithm,” SinkrOn, vol. 5, no. 1, pp. 164–169, Oct. 2020, doi: 10.33395/sinkron.v5i1.10621.