Fake it Till You Make it: Reputation, Competition, and Yelp Review Fraud

Abstract

Consumer reviews are now part of everyday decision-making. Yet, the credibility of these reviews is fundamentally undermined when businesses commit review fraud, creating fake reviews for themselves or their competitors. We investigate the economic incentives to commit review fraud on the popular review platform Yelp, using two complementary approaches and datasets. We begin by analyzing restaurant reviews that are identified by Yelp's filtering algorithm as suspicious, or fake -and treat these as a proxy for review fraud (an assumption we provide evidence for). We present four main findings. First, roughly 16% of restaurant reviews on Yelp are filtered. These reviews tend to be more extreme (favorable or unfavorable) than other reviews, and the prevalence of suspicious reviews has grown significantly over time. Second, a restaurant is more likely to commit review fraud when its reputation is weak, i.e., when it has few reviews, or it has recently received bad reviews. Third, chain restaurants -which benefit less from Yelp -are also less likely to commit review fraud. Fourth, when restaurants face increased competition, they become more likely to receive unfavorable fake reviews. Using a separate dataset, we analyze businesses that were caught soliciting fake reviews through a sting conducted by Yelp. These data support our main results, and shed further light on the economic incentives behind a business's decision to leave fake reviews. † We are thankful for helpful feedback from seminar participants at Berkeley Haas, IIOC, MIT Sloan, NYU Stern, and Wharton, as well as Lorin Hitt, an anonymous AE, and two referees.

Impact of reviewer social interaction on online consumer review fraud detection

“…An analysis on online review elasticity [43] present that volume and valence elasticity is higher for lesser known products which are sold by a couple of online retailers and that volume elasticity is higher on the product market whereas valence elasticity is higher on community markets. A very recent approach to identify fraud in Yelp reviews addresses the economic incentives for a particular business to conduct review fraud [27], Luca and Zervas with the help of the information provided by Yelp about one of it's sting operations derive that filtered reviews on Yelp tend to lie on extremes and that a restaurant is more likely to commit review fraud when it's reputation is relatively weak, basically when it has less reviews. They also discover that restaurants that have a chain are less likely to be involved in fraudulent activities and increased competition for a restaurant also increases the number of unfavorable fake reviews.…”

“…Recent study by Luca and Zervas has estimated the evidence of review fraud and the conditions under which it is most prevalent. They assembled two complementary datasets from Yelp and provided empirical support for using filtered reviews as a proxy for review frauds [27]. We have grouped collected review datasets into reviews by the recommended review group (non-spam) and reviews by the fake review group (filtered).…”

Social Media Management

“…6). For instance, organizations might write reviews themselves or pay someone else to do so in order to create an impression of peer consensus (Luca and Zervas 2014). Or organizations might pay bloggers for removing a blog post containing a negative review.…”

Comparative Analysis of User‐Generated Online Yelp Reviews for Periodontal Practices in Multiple Metropolitan Markets

“…The Yelp website has 165 million unique monthly visitors 2 and affords dental practices the opportunity for significant direct consumer exposure. Studies have documented the ability of positive Yelp reviews to improve business results 3 , 4 . Unfortunately, this has encouraged many businesses to manipulate their Yelp reviews to achieve financial gains 5 .…”

“…Unfortunately, this has encouraged many businesses to manipulate their Yelp reviews to achieve financial gains 5 . To counter such fraudulent activity, Yelp uses proprietary computer algorithms to identify and eliminate suspected illegitimate reviews, a process termed “filtering.” 3 , 5 When presenting reviews to the public, Yelp sequesters filtered reviews, identifies them as “non‐recommended reviews,” and does not include them when rating listed businesses on their website. When rating listed business, Yelp only uses “unfiltered” reviews – reviews that Yelp computer algorithms consider legitimate – and presents them to the public as “recommended reviews.” A previous pilot study 6 examined review characteristics and filtering rates of more than 2,000 reviews of dental practices based in Austin, Texas on the Yelp website.…”