Abstract

This paper focuses on the aspect of product defect detection as an essential capability for manufacturers to guarantee customer satisfaction with the quality of products. Successful product defect detection helps companies in avoiding expensive recalls, improving product quality, and building trust with consumers. The rapid rise in the use of e-commerce platforms results in the production of a large amount of information related to product defects from dissatisfied customers and negative feedback. Specifically, customer reviews contain rich information in the form of unstructured data, providing in-depth information on the practical application and product defect problems affecting purchasing decisions. The current study presents an extensive literature review on extracting information about product defects from customer reviews using machine learning approaches. The literature review includes traditional machine learning models, e.g., logistic regression, support vector machines, random forest, and gradient boosting models, as well as deep learning models, including but not limited to convolutional neural networks and long short-term memory networks. More recently, the study includes the application of transformer-based models, including BERT and its variants, because of their strong ability to understand context. The results of the analyzed papers show that deep learning approaches as well as transformer techniques always excel the performance of traditional approaches in the detection of both explicit as well as implicit product defects. This is because the application of the attention mechanism as well as the transformer technique results in better recall as well as F1 score values, making them more useful in the early detection of product defects in highly imbalanced review datasets. The results also manifest important implications related to machine learning in enhancing the detection of product defects, higher product quality, and optimized customer satisfaction.

References

• Kaburuana, E. R., Sari, Y. S., & Agustinaa, I. (2022). Sentiment Analysis on Product Reviews from Shopee Marketplace using the Naïve Bayes Classifier.‏
• Vasić, N., Kilibarda, M., & Kaurin, T. (2019). The influence of online shopping determinants on customer satisfaction in the Serbian market. Journal of theoretical and applied electronic commerce research, 14(2), 70-89.‏
• Jayadianti, H., Kaswidjanti, W., Utomo, A. T., & Saifullah, S. (2022). Sentiment analysis of Indonesian reviews using fine-tuning IndoBERT and R-CNN. ILKOM Jurnal Ilmiah, 14(3).‏
• Rangsang, R. A., & Millayani, H. (2021). The Effect Of Online Consumer Review On Customer Purchase Decision Process In The E-commerce Site Blibli. com. eProceedings of Management, 8(6).
• Ahmad, W. (2022). Improving Detection Accuracy for Fake Customer Product Reviews (Doctoral dissertation, The George Washington University).
• Fong, T. H. Y., Sarkani, S., & Fossaceca, J. (2021). Auto Defect Detection Using Customer Reviews for Product Recall Insurance Analysis. Frontiers in Applied Mathematics and Statistics, 38.
• Williams, H. (2021). Predicting Product Recall by Using Machine Learning to Analyze Customer Reviews (Doctoral dissertation, The George Washington University).
• Fong, T. H. Y. (2020). Identifying Product Defects by Applying a Predictive Model to Customer Reviews (Doctoral dissertation, The George Washington University).
• Zhang, X., Qiao, Z., Ahuja, A., Fan, W., Fox, E. A., & Reddy, C. K. (2019, May). Discovering product defects and solutions from online user generated contents. In The World Wide Web Conference (pp. 3441-3447).
• Qiao, Z., Zhang, X., Zhou, M., Wang, G. A., & Fan, W. (2017). A domain oriented LDA model for mining product defects from online customer reviews.
• Zhang, X., Qiao, Z., Tang, L., Fan, W. P., Fox, E. A., & Wang, G. A. (2016). Identifying product defects from user complaints: A probabilistic defect model. Department of Computer Science, Virginia Polytechnic Institute & State University.
• Ma, Y., & Li, F. (2012, October). Detecting review spam: Challenges and opportunities. In 8th International Conference on Collaborative Computing: Networking, Applications and Worksharing (CollaborateCom) (pp. 651-654). IEEE.
• Zheng, L., He, Z., & He, S. (2020). A novel probabilistic graphic model to detect product defects from social media data. Decision Support Systems, 137, 113369.
• Liu, Y., Jiang, C., & Zhao, H. (2018). Using contextual features and multi-view ensemble learning in product defect identification from online discussion forums. Decision Support Systems, 105, 1-12.
• Abrahams, A. S., Jiao, J., Fan, W., Wang, G. A., & Zhang, Z. (2013). What's buzzing in the blizzard of buzz? Automotive component isolation in social media postings. Decision Support Systems, 55(4), 871-882.
• Zhang, X., Niu, S., Zhang, D., Wang, G. A., & Fan, W. (2015). Predicting vehicle recalls with user-generated contents: A text mining approach. In Intelligence and Security Informatics: Pacific Asia Workshop, PAISI 2015, Ho Chi Minh City, Vietnam, May 19, 2015. Proceedings (pp. 41-50). Springer International Publishing.
• Pedregosa, F., Varoquaux, G., Gramfort, G., et al. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
• LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444.
• Torres, P., & Singh, K. (2025). Automated mining of consumer safety signals using LSTM and topic modeling. IEEE Internet of Things Journal, 12(8), 16744–16756.
• Zhang, D., Li, H., & Wang, H. (2023). A hybrid machine learning approach for defect detection in product reviews. Expert Systems with Applications, 225, 120109.
• Abrahams, A. S., Jiao, J., Fan, W., Wang, G. A., & Zhang, Z. (2013). What's buzzing in the blizzard of buzz? Automotive component isolation in social media postings. Decision Support Systems, 55(4), 871-882.
• Zhang, X., Niu, S., Zhang, D., Wang, G. A., & Fan, W. (2015). Predicting vehicle recalls with user-generated contents: A text mining approach. In Intelligence and Security Informatics: Pacific Asia Workshop, PAISI 2015, Ho Chi Minh City, Vietnam, May 19, 2015. Proceedings (pp. 41-50). Springer International Publishing.
• Mahesh, B. (2020). Machine learning algorithms-a review. International Journal of Science and Research (IJSR).[Internet], 9, 381-386.‏
• Dridi, S. (2021). Supervised Learning-A Systematic Literature Review
• Kotsiantis, S. B., Zaharakis, I., & Pintelas, P. (2007). Supervised machine learning: A review of classification techniques. Emerging artificial intelligence applications in computer engineering, 160(1), 3-24.
• Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press.
• Anas, S. M., & Kumari, S. (2021, January). Opinion mining based fake product review monitoring and removal system. In 2021 6th International Conference on Inventive Computation Technologies (ICICT) (pp. 985-988). IEEE.
• McCallum, Andrew. "Graphical Models, Lecture2: Bayesian Network Represention" (PDF). Retrieved 22 October 2019.
• Hammad, A. S., Tajammul, A., Dergaa, I., & Al-Asmakh, M. (2025). Machine learning applications in the analysis of sedentary behavior and associated health risks. Frontiers in Artificial Intelligence, 8, 1538807.‏
• Li, H., Zhang, D., & Wang, H. (2025). Transformer-based defect detection from online customer reviews using BERT. Expert Systems with Applications.
• Zhao, Q., Sun, M., & Zhou, Y. (2024). Real-time defect detection from streaming customer reviews using online learning. IEEE Transactions on Industrial Informatics.
• Alvarez, M., Chen, Y., & Gupta, R. (2024). Transformer-based product defect detection from large-scale e-commerce reviews. Information Processing & Management, 61(1).
• Wang, S., Liu, J., & Park, Y. (2024). Multilingual product defect detection using cross-lingual transformer models. Knowledge-Based Systems, 284.
• Hernandez, L., & Kim, J. (2024). Explainable deep learning for product defect detection using attention-based BiLSTM and SHAP. Applied Soft Computing, 145.
• Singh, R., Patel, A., & Mehta, S. (2024). Hybrid topic modeling and deep learning for early defect signal extraction. Pattern Recognition Letters, 176.
• Zhang, D., Li, H., & Wang, H. (2023). A hybrid machine learning framework for defect detection in product reviews. Expert Systems with Applications, 225, 120109.
• Chen, Y., Xu, L., & Zhao, H. (2023). Attention-based LSTM networks for implicit product defect detection. Neurocomputing, 512, 35–47.
• Fong, T. H. Y., Sarkani, S., & Fossaceca, J. (2023). Temporal modeling of online customer reviews for early defect detection. Decision Analytics Journal, 7.