Fake Reviews Detection Using Supervised Machi...

Fake Reviews Detection Using Supervised Machine Learning

Author Name : G .Venkatesh, Ms. G. Bhanu Priya

ABSTRACT

With the advancement of E-commerce systems, online evaluations are increasingly being viewed as a critical aspect in establishing and maintaining a positive reputation. They also play an important part in the decision-making process for end users. A positive evaluation for a target object usually draws more customers and results in a significant rise in sales. Nowadays, deceptive or fraudulent reviews are published on purpose to boost a company's virtual reputation and attract new clients. As a result, detecting false reviews is an active and ongoing research topic. Fake reviews can be identified not only by looking at the important aspects of the reviews, but also by looking at the reviewers' behaviour.The purpose of this paper is to offer a machine learning strategy for detecting false reviews. In addition to the review features extraction approach, this research uses different features engineering techniques to extract diverse reviewer behaviours. The research analyses the performance of machine learning classifiers such as KNN, Naive Bayes (NB), and Logistic Regression in numerous experiments conducted on a genuine Yelp dataset of restaurant reviews. In terms of accuracy, the results show that Logistic Regression surpasses the rest of the classifiers. The results demonstrate that the system is more capable of determining whether a review is fraudulent or genuine.

KEYWORDS: Machine learning, fake, reviews, Logistic Regression