Fakespot is a data analytics company committed to changing the way people read reviews and other content.
We believe that authentic user reviews are just about the best thing to come out of the Internet. But the user review system is too often abused by sellers that pay for reviews, by companies trying to make their competition look bad, and technologies that go around pretending to be real reviewers. Our patented algorithms looks for certain patterns that allow us to identify reviews we think are unreliable.
In just seconds, Fakespot can look through all of the reviews for any product or service on Yelp™ or Amazon™ and tell you whether the reviews are generally reliable or generally unreliable through our familiar letter grade system. It would take you months to look through all of that data. It’s better for everyone if you spend your time shopping online, going to restaurants and enjoying life. But don't take our word for it - you be the judge.
No. Fakespot does not review any products or companies. We only grade the product reviews.
Fakespot uses numerous technologies to evaluate the authenticity of reviews. The primary criteria are (1) English language pattern recognition, (2) the profile of the reviewer and (3) correlation with other reviewer data. Our algorithm uses machine learning to constantly improve itself by looking at profile clusters, sentiment analysis and cluster correlation. We use artificial intelligence that has been trained to pick up on patterns. The more data that flows into the system, the better the system gets at the detecting fakes.
No. The algorithms run through multiple tests to determine if a review is authentic or not. It’s rarely just a key word that sets off the alarm, it is a pattern of usage, or the repetition of certain words. Linguistics play a huge part in every analysis, but it is far more complex than just looking for certain keywords.
Amazon™, Yelp™, TripAdvisor™ and Apple™ App Store™. We are developing tools for other platforms, so keep an eye out as we add more!
Yes, Fakespot currently supports Amazon.com, Amazon.co.uk, Amazon.ca, Amazon.com.au and Amazon.in.
On Amazon, when the system associates a product review with a product purchase, that review is from a "verified purchaser". These reviews are in most cases reliable, since Amazon has already confirmed an actual purchase of the product being reviewed. On the flip side, if an Amazon review is not from a ‘verified purchaser’ there is no way of knowing for sure if the reviewer even used the product. While it is possible that a reviewer could have purchased the product elsewhere and left a review on Amazon at a later date, without purchase verification, it is impossible to tell. Also, our system has shown that most paid reviews come from unverified purchasers. In our opinion, dishonesty is likely when an Amazon review is not associated with a verified purchase.
Amazon Vine Reviews are flagged because we believe Amazon’s own Vine program is flawed and opaque. For Amazon sellers, they pay anywhere from $2,500 to $7,500 per product, plus provide free product in order to participate in the program. So, it's a pay-for-review program administered by Amazon itself. But, it's not clear how many sellers participate, nor is it clear how many products are sent out for reviews. You can find more information here.
For Vine reviewers, it is an invite-only program and participants are supposedly chosen at random by Amazon to join the program. All Vine reviewers get free product to review - although now reviewers have to pay taxes on them as gifts according to Amazon. It's essentially a reviews club run by Amazon, for Amazon customers, promoting fee paying Amazon sellers. You can find out more about the Vine program here. And as an Amazon Vine reviewer, you can list a public email and receive more solicitations for reviews from vendors not in the Vine program. Which means, a Vine reviewer who leaves positive reviews more often is regularly solicited to write more positive reviews by sellers seeking that extra bit of review credibility.
We flag Discount Disclaimer reviews because these reviews are essentially paid reviews. Even if there is a disclaimer by the reviewer, all we know for sure is that (1) The reviewer did not pay full price for the product, and (2) the reviewer may not have even considered to buy the product if not for the promotion. Most reviewers who leave promotional reviews rarely leave only a single promotional review. We have found that some discount reviewers manipulate their own Amazon reviewer profile by carefully sprinkling in one and two-star reviews in order to appear truly objective, which is why reviewers who leave promotional reviewers cannot be considered reliable. Find out more about one reviewer's experience here. In fact, Amazon has recently banned discount disclaimer reviews altogether. You can read the new guidelines from Amazon here.