One of the things that the UK Competition and Markets Authority (CMA) reported when it recently started to look into fake online reviews: smaller businesses are at higher risk of getting victimized, given that they can’t always afford the sophisticated systems that identify bogus reviews.
In fact, the online retailer on Friday introduced a new artificial intelligence system it developed in-house.
The purpose of the machine-learning platform is to surface the newer and most helpful reviews, which in turn will hopefully beat back astroturfers and make customers less skeptical of the veracity of its reviews.
In an interview with CNET, Amazon spokeswoman Julie Law said that the fraud detection system should get better over time as it learns what a good review is:
The system will learn what reviews are most helpful to customers...and it improves over time. It's all meant to make customer reviews more useful.
The changes to star ratings are expected to be gradual.
The new system will reportedly give more weight to newer reviews, reviews from verified Amazon purchasers, and those reviews that get voted as being “helpful” by more customers.
Weighting reviews will also figure into how a product’s starred rating gets calculated.
Previously, the rating was simply an average of all reviews. Going forward, star ratings will instead take into account the weighting of reviews.
Of course, if Amazon plans to rely on the “verified purchaser” label as one component in this new weighting scheme, it’s got to make sure that the label actually means what it says.
It doesn’t always, as court documents have recently shown.
In April, for the first time ever, Amazon sued sites that sell fake reviews.
In the complaint, Amazon accused one of the businesses of advising customers to “do a few verified purchase reviews … so as not to raise any eyebrows with [A]mazon.”
The reviewers don’t actually have to receive the products, customers buying the fake reviews were allegedly told.
Rather, they could just send empty boxes to try to fool Amazon into thinking that the reviewer was a “verified purchaser.”
Another fly in the ointment was brought up by commenters on the CNET story.
Namely, it’s the flip side of the “helpful” coin: the shills, and unpaid fanboys and girls, who are suspected of voting down critical reviews as being “not helpful,” thus promising to send them to the bottom in Amazon’s weighting scheme.
From commenter @RobertJCrowley:
Paid shills and unpaid fanboys/girls. And it doesn't have to be critical. On more than one occasion I've had objective, helpful three-star reviews of a middle-of-the-road book down voted into oblivion by the author's rabid fans.
The system initially will be confined to the US. It’s not clear yet if or when Amazon will bring it online in other countries.
Image of Amazon boxes courtesy of Joe Ravi / Shutterstock.
7 comments on “Amazon uses artificial intelligence to weed out fake reviews”
I’m more concerned about Amazon selling me gray imports without telling me than a fake review.
Weird how Amazon cares all of a sudden. Occasionally in the past I’d run into obviously fake reviews by reviewers that submit (on average) 20 product reviews a day. I’d report them to Amazon’s otherwise awesome customer service. I never would hear a response, and the reviews and reviewers would live to be a waste of time for future shoppers.
I recently clicked on a ‘Tell us what you think’ button to let them know a reviewer was an obvious fake. I had a reply within hours. I didn’t follow up to see if the reviewer account was booted, though.
Fake reviews are ruining what was once a very helpful source of info. At least I guess Consumer Reports will be relevant once again for more than cars.
I hope they take into account the fact that great many just do not give reviews of their purchases. If the item(s) is as described and arrives in the stated time, what’s to review? I do occasionally submit scathing reviews when something has gone seriously wrong, such as non-delivery or the item is nothing like the description – but they are few and far between (one of each in the last 2 years) as most sellers/retailers are trying to be honest and make a sensible profit.
Amazon care about reviews, really?
The amount of people who complain about reviews not relevant to the product, eg Blu-ray movies that have VHS reviews, DVD reviews all bundled in there. It doesn’t even have the ability to filter the more relevant blu-ray reviews to the top. I honestly don’t think they have looked at their review system since it was put in place or they would see these pain points.
What about people reviewing the company or person who sells or made the product rather than reviewing the product itself? The I hate company X, even though I never bought their product, I suggest you also do the same because I disagree with them.
I don’t think I have ever seen a company giving it self an added cost that benefits its competitors.
What is to stop a customer from reading reviews from somewhere they are trustworthy then simply going elsewhere to buy it cheaper from a company that doesn’t have the cost of policing its own reviews?
Let’s say there are 10 companies and 1 polices its own reviews. That 1 company would be doing the other 9 a favor while giving themselves an extra cost the others don’t have.
If you think the majority of customers are “loyal” to anything but the best deal then how come Walmart, Amazon, eBay are so big?
Profit margins are already razor thin!
For this to be credible at all, I have to assume it costs little / no time and money for Amazon AND be effective, or for anyone other company that apparently suddenly decides to police its own reviews.