A Survey on Spam Review Detection using Machi...

A Survey on Spam Review Detection using Machine Learning Techniques

Author Name : Vrinda Vyas, Pranali Patil, Tushar Bendarkar, Anand Rathi

ABSTRACT

In the current era of e-commerce online reviews play a very important role for decision making. Today online reviews are the huge source of social proof which results clear impact on sales and also build the reputation of an organization. Many customers are actually taking reviews before buying any product or visiting a business site. Because fake and fraudulent reviews come with capital gain. That's why spammers exploiting these reviews platform illegally. Positive reviews attract customers while negative reviews results in lower the demand and sells. Many sites are still not using filtering mechanism for the fake reviews. Yelp is a business secret which is an exception that over the past few years has filtered reviews. In this work by analyzing their filter reviews we try to find out what he could do and the results will  be useful in their filtering efforts for other reviews hosting sites. Filtering has two main approaches: supervised and monitored learning There are also about two types in terms of the characteristics used linguistic characteristics and behavioral characteristics. Through supervised learning approach we have tried to make a model which can identify the fake review with almost 70 percent of accuracy.

Keywords: Feature Engineering, Data mining, Spam Review