Spam Review Detection Using Machine Learning.

Information Science & Engineering

With the Covid-19 pandemic, massive lockdowns and social distancing tactics have contributed to an increase in the prevalence of the WWW and online service platforms. User-generated material, including customer reviews, has proliferated due to the proliferation of products and services offered by this digital world. These evaluations are extremely powerful, influencing both consumer choices and company product improvements. Nevertheless, inside this ecosystem, a harmful practice has surfaced, whereby certain entities utilize phony reviews—fake recommendations for their own products or false criticism of rivals'—in order to profit financially. The credibility of internet business is compromised by this dishonesty, which also misleads prospective customers. A strong system to identify and remove fake reviews is necessary to counter this threat. This research uses ML techniques to give a comprehensive framework for detecting bogus reviews. The objective of the suggested framework is to determine which categorization method is best suited to assign. Through a thorough examination of multiple machine learning algorithms, the framework aims to build a dependable system to differentiate between authentic and fraudulent reviews, protecting users' interests and promoting trust in online platforms.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.