CSEIT183113 | Received : 01 Jan 2018 | Accepted : 12 Jan 2018 | January-February-2018 [(3) 1 : 71-76]
International Journal of Scientific Research in Computer Science, Engineering and Information Technology
© 2018 IJSRCSEIT | Volume 3 | Issue 1 | ISSN : 2456-3307
71
A Survey on Challenges and Opportunistic Spotting Fake
Reviewer Groups in Consumer Reviews
P. Mrudula
*1
, B. Sankara Babu
2
*1
M.Tech, CSE, Gokaraju Rangaraju Institute of Engineering and Technology, Hyderabad, Telangana, India
2
Professor, CSE, Gokaraju Rangaraju Institute of Engineering and Technology, Hyderabad, Telangana, India
ABSTRACT
Online customer reviews for both products and merchants have greatly affected others decision making in purchase.
Considering the easily accessibility of the reviews and the significant impacts to the retailers, there is an increasing
incentive to manipulate the reviews, mostly profit driven. Without proper protection, group spam reviews will cause
gradual loss of credibility of the reviews and corrupt the entire online review systems eventually. Therefore, review
spam detection is considered as the first step towards securing the online review systems. In this paper, aim to
overview existing detection approaches in a systematic way, define key research issues, and articulate future
research challenges and opportunities for group review spam detection.
Keywords: Review Spam, Review Spammer, Spam Behavior.
I. INTRODUCTION
People's attitudes and opinions are highly influence
able by others, which is known as the word-of-mouth
effect in shaping decision making. The Internet and
Web-based technologies have created vast
opportunities to enable online word-of-mouth carriers
that play a critical role in influencing consumer
purchase decision in electronic commerce. People
exchange opinions about products or merchants in
online blogs, forums, social media, or directly post
reviews in various reputation systems provided by
individual online retailers, mega-retailers (e.g., eBay,
Amazon), or third-party sites (e.g., Bizrate,
resellerrating.com, Google+ Local, Yelp, etc.). Recent
surveys show that 83% of the consumers check out
online reviews to know about the products or
businesses they are buying from [1], and 80% of the
consumers have changed purchase decision due to
negative reviews [2].
Given the user-generated nature of online reviews and
the increasing impact on purchase decision making, the
quality and credibility of the reviews becomes a
primary concern. Many review sites allow consumers
to rate products or stores, write detailed comments, or
assess others' reviews (e.g., labeling as "helpful") to
express individual opinions. The ratings and reviews
are highly subjective and often individually biased.
Moreover, with profit incentives, unreliable reviews
with dishonest ratings, known as review spams, are
intentionally inserted into online review systems, e.g.,
product manufacturers, competitors or professional
online reputation management companies may fake
false positive (a.k.a ballot stuffing) or maliciously
negative reviews (a.k.a. bad mouthing) to promote or
demote a product, or to attract customers to a store or
distract them from competitors. Driven by profits, a
large number of spam reviews inserted manually or
automatically by professional review management
companies have been observed on many well-known
online reputation systems. The gradual loss of
credibility of online reviews will keep confusing the
consumers with poor or wrong assessment and
eventually cause the corruption of the review system.
Review spam detection is the first step towards
securing the online review systems. In this paper, we
aim to overview existing detection approaches in a
systematic way, define key research issues, and
articulate future research challenges for review spam
detection.