• Amirthavarshini B
• Perumal P
• Anu Deepthi V
• Brinda Iswarya Lakshmi R

Online customer reviews have a big impact on what consumers decide to buy in the current digital age. But as the significance of these reviews has grown, so too has the prevalence of phony ratings, which are posted by companies hoping to discredit rivals or enhance the reputation of their own goods. Such dishonest tactics are quite dangerous, especially for small businesses, where even one bogus negative review can have a significant negative impact. In response, this work uses machine learning (ML) techniques to propose an innovative way of identifying and categorizing bogus reviews. The Kindle dataset with a focus on book sales was used to test the suggested algorithm. A rigorous preparation workflow that included stemming, tokenization, normalization, and stop word removal was applied to textual data. For the classification, three machine learning methods were applied: BI Long Short Term Memory, Stochastic Gradient Descent and Gradient Boosting. Accuracy was assessed using methods for oversampling and under sampling both balanced and unbalanced datasets. The research's conclusions offer positive prospects for enhancing the credibility of online reviews and shielding businesses from the damaging effects of fraudulent evaluations. By revealing phony reviews, this study safeguards the interests of businesses and customers while also preserving the integrity of online review systems.

Fake Reviews, Fake Review Detection, Fake Product Detection, Detect Fake Reviews, Stochastic Gradient Descent(SGD), BI-LSTM, Gradient Boosting

"Fake Review Detection Using SGD", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.n462-n466, April-2024, Available :http://www.jetir.org/papers/JETIR2404D56.pdf

"Fake Review Detection Using SGD", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppn462-n466, April-2024, Available at : http://www.jetir.org/papers/JETIR2404D56.pdf