Performance Evaluation of Naive Bayes, SVM, LSTM, and IndoBERT for Fashion Review Sentiment Classification
-
Muhammad Iqbal Ismail
*
Universitas Pamulang, Tangerang Selatan,
Indonesia
- Denies Susanto Universitas Pamulang, Tangerang Selatan, Indonesia
- Indar Riyanto Universitas Pamulang, Tangerang Selatan, Indonesia
- Melinne Maldini Rosady Universitas Pamulang, Tangerang Selatan, Indonesia (*) Corresponding Author
Abstract
The rapid growth of e-commerce has increased the volume of customer reviews, making it difficult for fashion businesses to manually identify customer sentiment, product concerns, and satisfaction drivers. This study aims to evaluate the performance of Naive Bayes, Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and IndoBERT in classifying sentiment polarity in Indonesian fashion product reviews, while also identifying topic-level sentiment patterns using Latent Dirichlet Allocation (LDA). The dataset consisted of 23,487 Shopee Indonesia fashion reviews collected during the 2025 observation period. After data cleaning, duplicate removal, text normalization, tokenization, stopword removal, and lemmatization, 22,961 valid reviews were retained and categorized into positive, neutral, and negative classes using rating-based labeling. To reduce majority-class bias, stratified data splitting and class-weighted learning were applied, while five-fold cross-validation was used to evaluate model stability. The results show that IndoBERT achieved the highest performance with an accuracy of 93.41%, precision of 92.87%, recall of 92.15%, and F1-score of 92.51%, outperforming LSTM with 90.80% accuracy, SVM with 88.90%, and Naive Bayes with 84.60%. The findings indicate that transformer-based contextual representation is more effective in handling noisy Indonesian fashion review text, including informal expressions, abbreviations, and context-dependent sentiment. Topic-based analysis further revealed that positive sentiment was mainly associated with product quality, material comfort, design, and value, while negative sentiment was driven by sizing mismatch, product inconsistency, delivery delay, and customer service issues. This study contributes to sentiment classification research by providing a comparative evaluation of machine learning, deep learning, and transformer-based models, and offers practical insights for improving fashion e-commerce product communication, customer satisfaction, and data-driven digital marketing decisions.
Downloads
References
M. Kuang, R. Safa, S. A. Edalatpanah, and R. S. Keyser, “A hybrid deep learning approach for sentiment analysis in product reviews,” Facta Universitatis, Series: Mechanical Engineering, vol. 21, no. 3, pp. 479–500, 2023, doi: https://doi.org/10.22190/FUME230901038K.
V. Shobha Rani, K. Deepthi, V. Ramu, and G. Shirisha, “Sentiment Forecasting in Women’s Fashion E-Commerce: A Machine Learning Perspective,” in Multi-Strategy Learning Environment (ICMSLE 2024), Singapore: Springer, 2024, pp. 597–610, doi: 10.1007/978-981-97-1488-9_44.
M. Sharma, N. Sharma, and P. Verma, “Visualizing trends and correlation between fashion features for product design prediction using classification and sentiment analysis,” Computer Sciences & Mathematics Forum, vol. 12, no. 1, Art. no. 16, 2025, doi: https://doi.org/10.3390/cmsf2025012016.
Y. Zou, D. B. Luh, and S. Lu, “Public perceptions of digital fashion: An analysis of sentiment and Latent Dirichlet Allocation topic modeling,” Frontiers in Psychology, vol. 13, Art. no. 986838, 2022, doi: https://doi.org/10.3389/fpsyg.2022.986838.
Z. Nawaz, C. Zhao, F. Nawaz, A. A. Safeer, and W. Irshad, “Role of artificial neural networks techniques in development of market intelligence: A study of sentiment analysis of eWOM of a women’s clothing company,” Journal of Theoretical and Applied Electronic Commerce Research, vol. 16, no. 5, pp. 1862–1876, 2021, doi: https://doi.org/10.3390/jtaer16050104.
R. H. Chowdhury, “Sentiment analysis and social media analytics in brand management: Techniques, trends, and implications,” World Journal of Advanced Research and Reviews, vol. 23, no. 2, pp. 287–296, 2024, doi: https://doi.org/10.30574/wjarr.2024.23.2.2369.
V. Gooljar, T. Issa, S. Hardin-Ramanan, and B. Abu-Salih, “Sentiment-based predictive models for online purchases in the era of Marketing 5.0: A systematic review,” Journal of Big Data, vol. 11, no. 1, Art. no. 107, 2024, doi: https://doi.org/10.1186/s40537-024-00947-0.
S. Elzeheiry, W. A. Gab-Allah, N. Mekky, and M. Elmogy, “Sentiment analysis for e-commerce product reviews: Current trends and future directions,” Preprints, 2023, doi: https://doi.org/10.20944/preprints202305.1649.v1.
M. A. Al Montaser, B. P. Ghosh, A. Barua, F. Karim, B. C. Das, R. E. R. Shawon, and M. S. R. Chowdhury, “Sentiment analysis of social media data: Business insights and consumer behavior trends in the USA,” Edelweiss Applied Science and Technology, vol. 9, no. 1, pp. 545–565, 2025, doi: https://doi.org/10.55214/25768484.v9i1.4164.
L. Bharadwaj, “Sentiment analysis in online product reviews: Mining customer opinions for sentiment classification,” International Journal of Multidisciplinary Research, vol. 5, no. 5, 2023, doi: https://doi.org/10.36948/ijfmr.2023.v05i05.6090.
M. Selimovic, A. A. Almisreb, and S. Amanzholova, “The Role of Sentiment Analysis in Brand Management and Marketing: A Comparative Study,” Procedia Computer Science, vol. 251, pp. 579–584, 2024, doi: 10.1016/j.procs.2024.11.152.
T. Oyeku, “Unveiling customer sentiments in fast fashion: A comparative analysis of customer reviews, recommendations, and ratings,” Ph.D. dissertation, Dublin Business School, Dublin, Ireland, 2024. https://hdl.handle.net/10788/4583
K. S. Kyaw, P. Tepsongkroh, C. Thongkamkaew, and F. Sasha, “Business intelligent framework using sentiment analysis for smart digital marketing in the e-commerce era,” Asia Social Issues, vol. 16, no. 3, Art. no. e252965, 2023, doi: https://doi.org/10.48048/asi.2023.252965.
S. Erikson and W. Lam, “Sentiment analysis in digital marketing: Evaluating success dimensions of sentiment analysis and its role in digital marketing,” 2024. https://lup.lub.lu.se/student-papers/record/9162621
R. Paul, M. H. Imam, and A. J. Mou, “AI-powered sentiment analysis in digital marketing: A review of customer feedback loops in IT services,” American Journal of Scholarly Research and Innovation, vol. 2, no. 2, pp. 166–192, 2023, doi: https://doi.org/10.63125/61pqqq54.
C. Izumi, S. A. Ghaffar, and W. C. Setiawan, “Enhancing customer satisfaction and product quality in e-commerce through post-purchase analysis using text mining and sentiment analysis techniques in digital marketing,” Journal of Digital Market and Digital Currency, vol. 2, no. 1, pp. 1–25, 2025. https://doi.org/10.47738/jdmdc.v2i1.26
M. F. Farah, Z. Ramadan, W. Sammouri, and P. Tawk, “Digital luxury fashion shows: Leveraging interactive marketing opportunities through social media sentiment analysis,” in Digital Marketing & eCommerce Conference, Cham, Switzerland: Springer Nature Switzerland, 2024, pp. 23–30, doi: https://doi.org/10.1007/978-3-031-62135-2_4.
Y. A. Singgalen, “Social network and sentiment analysis of product reviews: Case of smartwatch product content,” International Journal on Social Science, Economics and Art, vol. 13, no. 4, pp. 255–267, 2024. doi: https://doi.org/10.35335/ijosea.v15i3
V. H. Luong, A. Tarquini, Y. Anadol, P. Klaus, and A. Manthiou, “Is digital fashion the future of the metaverse? Insights from YouTube comments,” Journal of Retailing and Consumer Services, vol. 79, Art. no. 103780, 2024, doi: https://doi.org/10.1016/j.jretconser.2024.103780.
Y. H. Choi, S. Yoon, B. Xuan, S. Y. T. Lee, and K. H. Lee, “Fashion informatics of the Big 4 Fashion Weeks using topic modeling and sentiment analysis,” Fashion and Textiles, vol. 8, no. 1, Art. no. 33, 2021, doi: https://doi.org/10.1186/s40691-021-00265-6.
O. Almashaleh, H. Wicaksono, and O. F. Valilai, “A framework for social media analytics in textile business circularity for effective digital marketing,” Journal of Open Innovation: Technology, Market, and Complexity, vol. 11, no. 2, Art. no. 100544, 2025, doi: https://doi.org/10.1016/j.joitmc.2025.100544.
H. N. D. Şenyapar, “Identifying pandemic era consumer trends: Sentiment analysis of social media posts,” Pamukkale Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, no. 61, pp. 191–213, 2024, doi: https://doi.org/10.30794/pausbed.1399760.
O. Bellar, A. Baina, and M. Ballafkih, “Sentiment analysis: Predicting product reviews for e-commerce recommendations using deep learning and transformers,” Mathematics, vol. 12, no. 15, Art. no. 2403, 2024, doi: https://doi.org/10.3390/math12152403.
M. Li, L. Zhao, and S. Srinivas, “It is about inclusion! Mining online reviews to understand the needs of adaptive clothing customers,” International Journal of Consumer Studies, vol. 47, no. 3, pp. 1157–1172, 2023, doi: https://doi.org/10.1111/ijcs.12895.
L. Theodorakopoulos and A. Theodoropoulou, “Leveraging big data analytics for understanding consumer behavior in digital marketing: A systematic review,” Human Behavior and Emerging Technologies, vol. 2024, no. 1, Art. no. 3641502, 2024, doi: https://doi.org/10.1155/2024/3641502.
H. Kim, I. Cho, and M. Park, “Analyzing genderless fashion trends of consumers’ perceptions on social media: Using unstructured big data analysis through Latent Dirichlet Allocation-based topic modeling,” Fashion and Textiles, vol. 9, no. 1, Art. no. 6, 2022, doi: https://doi.org/10.1186/s40691-021-00281-6.
M. M. Mariani and S. Nambisan, “Innovation analytics and digital innovation experimentation: The rise of research-driven online review platforms,” Technological Forecasting and Social Change, vol. 172, Art. no. 121009, 2021, doi: https://doi.org/10.1016/j.techfore.2021.121009.
V. Sharma and T. Manocha, “Comparative analysis of online fashion retailers using customer sentiment analysis on Twitter,” in Proceedings of the International Conference on Innovative Computing & Communication (ICICC), 2022. http://dx.doi.org/10.2139/ssrn.4361107
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: https://doi.org/10.1109/ACCESS.2023.3307308.
P. Akter, S. Hossain, M. T. Siddique, M. I. Ayub, A. Nath, P. C. Nath, and M. M. Hassan, “Sentiment analysis of consumer feedback and its impact on business strategies by machine learning,” The American Journal of Applied Sciences, vol. 7, no. 1, pp. 6–16, 2025, doi: https://doi.org/10.37547/tajas/volume07issue01-02.
Y. D. Nurcahyanie, M. L. Singgih, and D. S. Dewi, “Implementing online product reviews and Muslim fashion innovation for resilience during the new normal in Indonesia,” Sustainability, vol. 14, no. 4, Art. no. 2073, 2022, doi: https://doi.org/10.3390/su14042073.
R. Hasan, “Enhancing market competitiveness through AI-powered SEO and digital marketing strategies in e-commerce,” ASRC Procedia: Global Perspectives in Science and Scholarship, vol. 1, no. 1, pp. 465–500, 2025, doi: https://doi.org/10.63125/31tpjc54.
G. Sundareswaran, H. Kamaraj, S. Sanjay, A. Devi, and P. Elangovan, “Consumer behavior analysis: Analyze customer segmentation, sentiment on product review, and a product recommendation system,” International Journal of Research and Applied Technology (INJURATECH), vol. 2, no. 1, pp. 82–90, 2022, doi: https://doi.org/10.34010/injuratech.v2i1.6536.
C. Ziakis and M. Vlachopoulou, “Artificial intelligence in digital marketing: Insights from a comprehensive review,” Information, vol. 14, no. 12, Art. no. 664, 2023, doi: https://doi.org/10.3390/info14120664.
Y. Y. Raghav, R. K. Tipu, R. Bhakhar, T. Gupta, and K. Sharma, “The future of digital marketing: Leveraging artificial intelligence for competitive strategies and tactics,” in The Use of Artificial Intelligence in Digital Marketing: Competitive Strategies and Tactics, IGI Global Scientific Publishing, 2024, pp. 249–274, doi: https://doi.org/10.4018/978-1-6684-9324-3.ch011.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Performance Evaluation of Naive Bayes, SVM, LSTM, and IndoBERT for Fashion Review Sentiment Classification
Pages: 272-741
Copyright (c) 2026 Muhammad Iqbal Ismail, Denies Susanto, Indar Riyanto, Melinne Maldini Rosady
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- 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.
- 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.
- 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).
