Review Spam Detection by Highlighting Potential Spammers and Diminishing Their Effect

Review Spam Detection by Highlighting Potential Spammers and Diminishing Their Effect

Fatemeh Keshavarz (University of Calgary, Canada), Ayeshaa Abdul Waheed (University of Calgary, Canada), Btissam Rachdi (University of Calgary, Canada) and Reda Alhajj (University of Calgary, Canada and Global University, Lebanon)
Copyright: © 2018 |Pages: 23
DOI: 10.4018/IJEBR.2018010104
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Nowadays, millions of products and services are available to the public online. Therefore, searching for the best products which meets individuals' expectations would be difficult due to the existence of too many alternative choices. One of the most reliable approaches to choose a product or service is to exploit the experience of people who have already tried them, and are expected to have reported their almost honest opinions about them. A reviewing system is a place where individuals share their experience on products and services. Individuals may read and/or write their reviews which may be neutral and professional or biased. Moreover, companies utilize reviewing systems to apply opinion mining techniques in order to improve their goods or services and may be to watch their competitors. However, the popularity of reviewing systems ignites this motivation for some people to try to influence viewers by entering their fake reviews to promote some products or defame some others. These spam reviews should be detected and eliminated to prevent misleading potential customers and unethically affect the market. Opinion mining should be adapted to locate and eliminate potential spam reviews. In this paper, some review spam detection approaches have been proposed and examined over a sample dataset. The proposed approaches consider patterns that existed in trends of reviews, as well as reviewers' behavior. The approaches depend on various strategies such as observing abnormal trends, detecting uncommon or suspicious behaviors, investigating group activities, among others. The reported test results revealed some promising outcome.
Article Preview

Introduction

Almost immediately after the advent of the Internet and the Web technology, individuals as well as public and private organizations became interested in marketing their products and services on the Web. Since then, the utilization of the Web for selling products became rapidly pervasive such that nowadays it constitutes a considerable proportion of the Internet usage. Along with advertising on the Web and in addition to the independent sites that allow for product evaluation, vendors have given their audience the authority to evaluate and comment on the merchandise. Having this feature available and in most cases added to retailing websites, may be beneficial to both parties, i.e., producers and consumers. Companies can analyze the provided reviews to learn the strengths and weaknesses of their goods and services from consumers’ points of view. They can further apply their conclusions in future to achieve higher levels of satisfaction from consumers, as well as to attract more people towards buying their merchandise. Moreover, they can investigate purchasers’ reviews of products of competitor companies to become aware of the general appetite of consumers: their preferences, priorities, etc. Considering the admirable features of competing products in purchasers’ opinions, producers can improve their own products by adding or magnifying those features. Further, by becoming aware of discreditable characteristics of products from rival companies, manufacturers will make sure not to strengthen those characteristics in their production or maybe to consider deficiencies before they are realized by customers. On the other hand, since the ability to review products online is made available for people, they can easily post their comments on their desired products at any time, from any part of the world, and at their own convenience. Consequently, a large number of opinions with a significant variety of ranking may be encountered. This also gives at almost no cost the opportunity to competitors to watch how their products have been received by consumers. Possessing sentiments of previous consumers of different interests and expectations, individuals can distinguish their most preferred goods or services faster and straighter than the time when such an integrated collection of opinions was not available. Therefore, presently, individuals rely extensively on reviews available online. This means they decide whether to buy products or not by analyzing existing opinions on those products. In fact, when a potential customer gets a positive overall impression of a product by considering its present sentiments, it is highly probable that he/she will act more in favor of purchasing the product. Normally if the percentage of positive opinions is considerable, it is likely that the overall impression will be highly positive. Likewise, if the overall impression is negative, it is less imaginable that vendees buy the product. Again, the overall negative impression can be the result of a great proportion of negative sentiments. The results of a survey conducted in early 2012 indicate that 51% of the customers have used Internet more than 6 times during a year while 72% of them have the same trust in online reviews as they have in personal recommendations (Anderson, 2012).

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 14: 4 Issues (2018): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2017)
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing