Brett Hollenbeck is an economist at UC Los Angeles. He studies, among others, the economics and regulation of rating manipulation on online platforms and online reviews.
Photo courtesy Brett Hollenbeck
How do we spot fake product reviews
It’s actually quite difficult to tell what’s fake. People who write them have a strong financial incentive to bypass the Amazon filter. They’re going to write what seems like an authentic review. This is why a lot of the machine learning methods that have been trained to try to detect aspects of the text don’t work well. However, there are some things you could look out for to identify which products use them.
One thing we find is that the products that are getting fake reviews tend to get a lot of negative reviews as well—there’s something like a backlash going on. These products get a large number of one-star ratings. This is because the one-star reviews tend to be negative and not favourable reviews about the product’s quality. While this is true for other products, most one-star reviews about these products are due to idiosyncratic issues or bad customer service. It is helpful to ignore five-star reviews which are often fake.
You should also check out the most recent reviews. Because you’ll see fake positive reviews first, then more negative reviews as the time passes. So most likely the most recent reviews are the most accurate ones, and then you’re likely to get to the truth, which is probably the negative review, if this is a product that’s using fake reviews. If all the most recent ones are positive and seem real, and there’s not a lot of one-star reviews, then those are the products you would trust.
Our new study examines larger data sets on reviews and products to find unusual clustering within that network. This logic suggests that products purchasing fake reviews out of necessity must buy them from a small number. All products that are looking for fake reviews get reviews from these people. You can easily spot fake reviews by looking at this network.
We collected data from private Facebook groups where product sellers purchase fake reviews. Then we scraped a huge amount of data from Amazon on both the product and reviewer sides. You can see which products received reviews from which reviewers and which products these reviewers have reviewed.
Amazon has everything I need. Fake reviews were a problem I was aware of. I was unaware of its scale. Now I will look at a product, say a white-noise machine, and there’s like 10 other white-noise machines that look just like it. I can almost guarantee you they’re all buying fake reviews, and the ratings don’t mean anything.
I will often purchase the products. The question is: How bad could it be? It’s like an under-$20 purchase. Probably they’re buying fake reviews to compete with the other sellers in this category. But what’s the worst that can happen? For larger purchases, I don’t look at the Amazon reviews at all. Wherever there’s a financial incentive for it, we see this type of fraud. It’s just an inherent feature of two-sided markets.
So if it’s more than a certain dollar amount, I would be more likely to go off Amazon and look at critics’ lists or curated lists of product recommendations. These are trustworthy.
Image by EamesBot / Shutterstock
This article was published on November 29, 2022
Brian Gallagher is associate editor at Nautilus. Follow him @bsgallagher on Twitter
Get the Nautilus newsletter
Get the hottest and most requested articles straight to your inbox