Understanding the Yelp review filter: An exploratory study

Abstract

Reviews on Yelp.com can be an important factor in driving customers to a business. However, many business owners have expressed concern with Yelp's review filtering system, which was created to flag low-quality or fake reviews. This study performs a content analysis of a subset of Yelp restaurant and religious organization reviews, visible and filtered, exploring signals from the reviews or the reviewers that might explain the filtering process. The study finds that factors intrinsic to the review itself are not related to filtering, but factors related to the reviewer are strong predictors. The Yelp system is much more likely to filter reviews from occasional, isolated reviewers than from prolific, socially connected reviewers.

Do Crowdsourced Hospital Ratings Coincide with Hospital Compare Measures of Clinical and Nonclinical Quality?

“…In terms of the share of hospitals observed in the sample, 98 percent, 93 percent, and 90 percent of hospitals present on HC had a Google, Facebook, or Yelp rating, respectively. Yelp, established in 2004, applies a filter to reviews to proactively filter out false reviews (Kamerer ). Google reviews, established in 2012, allow users to leave reviews without an account and, subsequently, ratings were integrated with the Google search engine, raising their visibility.…”

User Attitudes towards Algorithmic Opacity and Transparency in Online Reviewing Platforms

“…However, the fact that many algorithmic systems (such as Yelp's review filter) are housed in black boxes poses a substantial challenge to outside researchers trying to evaluate different levels of transparency. While past research has attempted to reverse engineer the Yelp filtering algorithm [25], no ground truth is available to those outside Yelp.…”

The Impact of Fake Reviews on Online Visibility: A Vulnerability Assessment of the Hotel Industry

“…Given the ambiguity of previous findings, we conduct our own study on a dataset collected from Yelp.com, which applies a proprietary filter to identify fraudulent and other low-quality reviews (Kamerer 2014). Even though such reviews are not prominently displayed on the page of the reviewed business, they remain online and can be viewed by the interested user.…”

“…The policy of favoring recent reviews in review-based rankings is adopted by industry leaders such as TripAdvisor and Yelp (Kamerer 2014, Mukherjee et al 2013b. Therefore, the vulnerability of the PopularityIndex has major implications for these platforms and their users.…”