TY - GEN
T1 - Detecting and Classifying Fraudulent Product Reviews Based on Natural Language Processing
AU - Sauveur, Uwambazimana Chaste
AU - Chudasama, Chetankumar
AU - Verma, Deepak Kumar
AU - Chaudhary, Preeti
AU - Verma, Aditya
AU - Gupta, Himanshu
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.
PY - 2026
Y1 - 2026
N2 - E-commerce is experiencing rapid growth with a significant rise in online commerce. As more consumers turn to buying products online to save money and time, it has become common for customers to check product ratings and reviews before purchasing. The impact of reviews on purchasing decisions is evident as positive reviews tend to drive increased purchases, while negative ones can lead to a decline in sales. In those reviews, there is a risk of fraudulent reviews intended to benefit vendors by boosting sales and branding. This deceptive practice can increase counterfeit and abandoned products, often causing harmful effects on buyers. In response to this issue, we devised a spam review detection system using Natural Language Processing and a combination of classification algorithms that analyzes sentiment on the product review dataset by considering the posted date and the user who posted the review. The proposed model will classify human-generated text as genuine and machine-generated text as spam reviews. The case study is based on Amazon India’s E-commerce platform. The negative impact of fraudulent reviews on consumer confidence cannot be overstated, and we must address this issue to maintain the trust of online shoppers.
AB - E-commerce is experiencing rapid growth with a significant rise in online commerce. As more consumers turn to buying products online to save money and time, it has become common for customers to check product ratings and reviews before purchasing. The impact of reviews on purchasing decisions is evident as positive reviews tend to drive increased purchases, while negative ones can lead to a decline in sales. In those reviews, there is a risk of fraudulent reviews intended to benefit vendors by boosting sales and branding. This deceptive practice can increase counterfeit and abandoned products, often causing harmful effects on buyers. In response to this issue, we devised a spam review detection system using Natural Language Processing and a combination of classification algorithms that analyzes sentiment on the product review dataset by considering the posted date and the user who posted the review. The proposed model will classify human-generated text as genuine and machine-generated text as spam reviews. The case study is based on Amazon India’s E-commerce platform. The negative impact of fraudulent reviews on consumer confidence cannot be overstated, and we must address this issue to maintain the trust of online shoppers.
UR - https://www.scopus.com/pages/publications/105028273404
UR - https://www.scopus.com/pages/publications/105028273404#tab=citedBy
U2 - 10.1007/978-981-96-8799-2_31
DO - 10.1007/978-981-96-8799-2_31
M3 - Conference contribution
AN - SCOPUS:105028273404
SN - 9789819687985
T3 - Lecture Notes in Networks and Systems
SP - 401
EP - 411
BT - Machine Intelligence for Research and Innovations - Proceedings of MAiTRI 2024
A2 - Verma, Om Prakash
A2 - Wang, Lipo
A2 - Kumar, Rajesh
A2 - Yadav, Anupam
A2 - Rout, Ranjeet Kumar
PB - Springer Science and Business Media Deutschland GmbH
T2 - 2nd International Conference on Machine Intelligence for Research and Innovations, MAiTRI 2024 Summit
Y2 - 21 June 2024 through 23 June 2024
ER -