Ensemble Classifiers Employed for Spam Review Detection

Alhassan Jamilu Ibrahim,Maheyzah Siraj,Usman Abubakar Jauro

doi:10.11648/j.es.20210603.11

Abstract

The advancement of technology and the use of internet have changed many aspects of human culture over the years. Today, consumers take confidence in e-commerce platforms like amazon and eBay for comprehensive understanding of products and services when making a purchase decision. Here the web or user-generated content from consumers of such products and services, known as reviews, are exploited by spam reviewers to falsely promote or downgrade some targeted products. Despite potential solutions, Identifying and preventing review spam are still one of the top challenges faced by web search engines today. Therefore, in the quest to provide a more improved and efficient classification of review spam, this research probed different techniques in order to find most effective solution to spam detection. The research employed three base classifiers, Naïve Bayes, Support Vector Machines and Logistic Regression to form ensemble classifiers complimented with Arching classifier. The Arching classifier performs the weighted voting that produces the final class label with performance and accuracy higher than either of the individual base classifiers. Cross-validation is used as evaluation metrics to measure the performance or effectiveness of the ensemble classifiers while the experimental results shows that the ensemble classifiers achieve the best results compared to the single based classifier in terms of Precision, Recall, F1-measure and Accuracy.

Highlights

The world is witnessing more and more participation in modern electronic commerce, where online review is playing a vital role
This research presented the model, operational framework and the methodology of designing and investigating the architecture of an ensemble classifier to perform the function of spam review detection
The model was designed using Naïve Bayes, Support Vector Machine and Logistic Regression as base classifiers. These base classifiers are justifiably selected through the process of ‘bagging’, where each was assigned a weight depending on accuracy of prediction

Summary

Introduction

The world is witnessing more and more participation in modern electronic commerce, where online review is playing a vital role. Customers engage in reading reviews on products and stores when they are making decisions on what to buy or where to buy it. Spam reviewers seized this opportunity to write malicious reviews to discredit decent stores or use fake reviews to deceive customers on low quality products. This is often regarded as spam review. Opinion spamming or review spam are terms used in identifying fake reviews which were deliberately concocted to deceive potential users or opinion mining systems by providing them with undeserving positive opinions or false negative opinions to promote or downgrade some targeted products. Google pointed out concerns of fake reviews in an official report and clearly directed the innovators and users to not purchase and receive payments from firms that make available false reviews [15]

Objectives

Results

Conclusion