Home / Current Issue / Paper 1717765
A Unified Framework for Detecting Fake Reviews and Counterfeit Products in E-Commerce Platforms using Machine Learning
Subject area: Science,Engineering and Technology · Area of research: Machine Learning, Artificial Intelligence
DOI: https://doi.org/10.64388/IREV9I11-1717765
Abstract
The growth of shopping has changed how people buy things, but it has also brought new problems with trusting online sellers. Fake reviews and fake products are two issues for online marketplaces. Fake products hurt customers and good companies by making it hard to tell if a product is real, while fake reviews trick people who are thinking of buying something by changing the product ratings[6],[9]. Some studies have looked at these problems separately. Product companies have suggested using things like blockchain-based authentication, QR codes and image analysis to check if a product is real[13],[14]. For reviews, companies have used machine learning and natural language processing methods have been utilized to analyse reviews and find fake ones[1],[2],[10]. There is still a problem. No system checks whether a product is real. If reviews are trustworthy at the same time[13]. This makes it hard for online shopping platforms to really know if customers can trust what they are buying. This study suggests a way to look at both problems together. It wants to use computer analysis of reviews and checks on products to help online shopping platforms find and stop products and reviews. This can help people trust shopping more and make online marketplaces more open and honest. When we find and stop products and reviews, online shopping becomes safer for everyone. This is the thing for customers and businesses. Customers can trust the things that they buy online. Businesses also benefit from this because online shopping becomes reliable. This means that customers and businesses both can feel good about shopping online
Keywords
Fake Review Detection, Detecting Counterfeit Products, E-Commerce Security, Using Machine Learning, Understanding Natural Language Processing, Evaluating Trust, Fraud Detection
References
[1] S. B. Hyder, et al., “BERT-Based Deceptive Review Detection in Social Media: Introducing DeceptiveBERT,” IEEE Transactions on Computational Social Systems, 2024.
[2] A. Shalini and R. Roopa Chandrika, “Fake Product Review Prediction using BERT Enabled Multiattention CNN,” in Proceedings of the ICCAMS Conference, 2025.
[3] R. Gupta, et al., “Cross-Domain Fake Review Detection via Orthogonal Counterfactual Representations,” IEEE Access, 2025.
[4] I. Amin, I. Fakhr, M. W. Fakhr, and R. Kashef, “Boosting Arabic Fake Reviews Detection by Integrating Textual and Metadata Features,” IEEE Access, 2025.
[5] S. Sudha Mercy, et al., “LDCP: A Novel Approach to Predict Fake Reviews in Online Social Networks,” in Proceedings of the ICSES Conference, 2024.
[6] R. Sharma, et al., “Revealing the Reliability of Amazon Products via Innovative Fake Review Detection using Machine Learning,” in Proceedings of the ICICV Conference, 2025.
[7] K. T. Kumaragurubaran, et al., “Psychological-Based Opinion Mining for Fake Review Detection,” in Proceedings of the GINOTECH Conference, 2025.
[8] E. Abedin, et al., “Predicting Credibility of Online Reviews: An Integrated Approach,” IEEE Access, 2024.
[9] M. A. Balmukund, et al., “Smart Fake Review Detection with NLP, BERT and Behaviour Analysis,” in Proceedings of the ICAAIC Conference, 2025.
[10] R. Singhal and R. Kashef, “A Weighted Stacking Ensemble Model with Sampling for Fake Reviews Detection,” IEEE Transactions on Computational Social Systems, 2024.
[11] S. Zhang, et al., “Building Fake Review Detection Model Based on Sentiment Intensity and PU Learning,” IEEE Transactions on Neural Networks and Learning Systems, 2023.
[12] N. Giridharan, et al., “Online Multilingual Spam Review Detection using Twin Support Vector Machine,” in Proceedings of the ICAAIC Conference, 2024.
[13] S. G. Shanmukh, et al., “Fake Product and Fake Review Detection,” in Proceedings of the ICSCC Conference, 2025.
[14] “Research Study on Counterfeit Product Detection using Blockchain Technology,” Conference Paper, 2024.
[15] A. Qazi, et al., “Machine Learning-Based Opinion Spam Detection: A Systematic Literature Review,” IEEE Access, 2024.
How to cite this paper
@article{1717765,
author = {Pulkit Bahuguna, Dr. M N Nachappa},
title = {A Unified Framework for Detecting Fake Reviews and Counterfeit Products in E-Commerce Platforms using Machine Learning},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {11},
pages = {1929-1939},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1717765.pdf},
abstract = {The growth of shopping has changed how people buy things, but it has also brought new problems with trusting online sellers. Fake reviews and fake products are two issues for online marketplaces. Fake products hurt customers and good companies by making it hard to tell if a product is real, while fake reviews trick people who are thinking of buying something by changing the product ratings[6],[9]. Some studies have looked at these problems separately. Product companies have suggested using things like blockchain-based authentication, QR codes and image analysis to check if a product is real[13],[14]. For reviews, companies have used machine learning and natural language processing methods have been utilized to analyse reviews and find fake ones[1],[2],[10]. There is still a problem. No system checks whether a product is real. If reviews are trustworthy at the same time[13]. This makes it hard for online shopping platforms to really know if customers can trust what they are buying. This study suggests a way to look at both problems together. It wants to use computer analysis of reviews and checks on products to help online shopping platforms find and stop products and reviews. This can help people trust shopping more and make online marketplaces more open and honest. When we find and stop products and reviews, online shopping becomes safer for everyone. This is the thing for customers and businesses. Customers can trust the things that they buy online. Businesses also benefit from this because online shopping becomes reliable. This means that customers and businesses both can feel good about shopping online},
keywords = {Fake Review Detection, Detecting Counterfeit Products, E-Commerce Security, Using Machine Learning, Understanding Natural Language Processing, Evaluating Trust, Fraud Detection},
month = {May},
doi = {https://doi.org/10.64388/IREV9I11-1717765}
}