Detection of Fake Reviews Using Machine Learning Techniques

Abstract

Online marketing generates vast amounts of digital information, which is then used to advertise millions of goods and services. Finding the best services or goods that meet the need is, therefore, difficult. Customers make decisions based on evaluations or opinions expressed by third parties. In this cutthroat environment. For the past few years, some businesses have employed writers to fabricate favorable reviews of their services or goods or unfairly critical reviews of those of their rivals in order to increase the number of false reviews. Review sites are increasingly having to deal with the distribution of false information that either benefits or hurts particular firms. Different types of opinion spam are used to deceive both human readers and automated sentiment analysis and opinion mining systems. Different strategies have been put forth as a result, allowing for the evaluation of the user-generated content's credibility. The current paper provides a quick introduction to the examination of opinion mining and the review-centric attributes that have been suggested for use in machine learning techniques that use graphical methods to identify bogus reviews. Along with a review of the related literature and a discussion of it.