Since I haven't seen it posted yet, an invaluable tool for sifting through fake vs real Amazon reviews is fakespot.com. They use AI to score every product and crawl an item's review tree (reviews left by the same people for other products) to verify the authenticity of individual reviewers. I've sifted out a lot of shady products AND sellers using this. (I'm not affiliated in any way with them.)
Or paste the URL into FakeSpot. Although I have found FS to be incorrect at times, flagging reviews as legit when they clearly are not.
It's becoming more and more widely known that there are numerous items with fake reviews, and Amazon doesn't seem to care. I wonder if this might lead to their downfall?
Along with the counterfeit items[1] and poor price/review count sorting. As a made-up example, an item with three five star reviews can rank higher on sorting than an item with say one hundred reviews with an aggregate of 4.7 stars. I'd take the latter any day. And sort by price; it goes (another made-up example) $2, $2.50, $6, $3...
I like Amazon for Prime, the wide ocean of selection, the reviews -- when not fake. But caveat emptor.
If http://fakespot.com/ can spot fake reviews, Amazon themselves should be able to do it. It's in their long term interest that product reviews are genuine so that buyers have confidence. If I can't trust Amazon reviews, I'll just shop at Target where at least I can handle the physical product before I buy it.
I've taken to keeping a copy of Fakespot[0] open in an incognito browser and regularly submit Amazon URLs to it. Over the past month or so, I've looked at everything from headphones to shampoo and been boggled at the amount of rigging that goes on.
While I can't say for sure that their algorithms are always spot on, they give some interesting feedback in terms of recent review count history, price history, whether Amazon has recently bulk deleted reviews, and some heuristic comment quality ratings. So often I've found that Amazon's Choice is questionable: 4.8 stars, hundreds of reviews within the last 30 days on a slickly packaged, no-name electronics gadget is all too common.
Typically, I use Fakespot to look for red flags, flip back to the reviews area on Amazon, sort them by Most Recent Reviews, and dig around. I don't use the Fakespot Chrome extension, though. Too invasive for my tastes.
This is why I use tools like fakespot and reviewmeta to make sure Amazons reviews are somewhat accurate. Sure, it's not fool proof, but these tools attempt to filter the obvious bad reviews.
Amazon has a lot of paid-for reviews, so you would likely see it if you remove the paid entries.
In some cases on very bad products, you see tons of 5 star reviews and a lot of 1 star reviews - and if it's high on the fakespot list, I can only conclude it's a bad product.
I've mostly given up on Amazon except where I can't find the product elsewhere (or on time).
Amazon reviews have been shady for years. To combat this I never buy without running the item link through fakespot.com. The other day I also discovered reviewmeta.com t haven't tried it yet.
FakeSpot and ReviewMeta are up on different tabs every time I buy something new on Amazon, and they do a pretty good job of alerting you to scammy reviews without any internal Amazon info. I can’t imagine it’s not something an internal team could make a serious dent in.
Consider running fakespot against the reviews of them as well, because I straight up never buy commodity electronics on amazon without first checking to see how astroturfed the reviews are.
I'd imagine that it can't be too hard on Amazon's side to predict whether a product receives a lot of fake reviews or not. Just checking if the reviewer has other reviews would be a simple first step to grab the low-hanging fruit.
Amazon is a huge search engine. They should act like one and prevent attempts of gaming the system.
I left this comment on the site's comment section (apologies if others have already posted these suggestions - I didn't read through all the comments):
Try using fakespot.com or reviewmeta.com. They're both sites setup to try & check the validity of Amazon comments using different methodology - such as how many times a reviewer has left a review, certain trigger keywords known to be used by bots & how many reviews Amazon has deleted from a review by request of the merchant (yes, Amazon will do this!). This will leave you with a much better sense of whether or not a product has been 'review-bombed' or if the company is up to shady practices.
Thank you for being a Fakespot user. I thought I'd bring in some perspective to your question.
Your observation of the preponderance of unreliable reviews on Amazon matches what we see across the board.
Unfortunately, ever since Amazon opened up to 3rd party sellers, the reviews have become a marketing tool by a lot of these sellers to move ahead of other products. These sellers use everything from pure fake reviews to gamed verified purchase reviews. This is major reason why so many reviews nowadays are unreliable, it is truly a wild west out there in the eCommerce world and fake reviews can mean $$$.
With that said, we just launched Fakespot Guardian as part of our new Chrome extension which solves the 3rd party seller problem by telling you if a seller is reliable or not. By knowing if seller and reviews are reliable, you will be able to purchase anything with confidence.
> I'd like to know how it's possible for third-party sites such as https://www.fakespot.com to more effectively identify fake Amazon reviews while Amazon (with presumably better data) fails so miserably.
Maybe they can't? Fakespot authoritatively scores reviews but is there evidence that they are accurate? Anecdotally, there are many claims that the results aren't perfect, such as poor scores on a product where the seller knows there are no fake reviews. As a buyer the results on similar, shortlisted, products often seem a bit random compared to my judgement from reading the reviews carefully. Also, without knowing what reviews are identified and removed by amazon themselves we don't have much to compare it to.
Was just about to post fakespot.com -- I've used it to great benefit in spotting some of my purchases that didn't have a reasonably priced, stand-out name brand to choose from (HDMI -> RCA audio splitters, or as mentioned in this thread, good bluetooth wireless earbuds.
Amazon is consistently allowing multi-hundred unverified 5 star reviews for new products to persist, and my wife and I are starting to drift to other, more reputable resources. After a decade+ of Prime membership, this is a really disappointing betrayal of trust.
I did my dissertation on this very topic (coming soon to my website... at some point). I do not know what tactics or systems Amazon has that deal with fake reviews, or if they even really bother beyond the easy wins like tracking IPs. My dissertation was on textual analysis, which is the hard part - the other signals like IP and behavioral related ones (like # of reviews posted in one day) are more fruitful.
The heuristic you seem to be using is a logical one, but requires more data analysis than Amazon might be willing to put effort into. Looking at these reviews, they are... well, so many on the same day is suspicious. My first theory is that some fake review writing company got tasked with flooding Amazon, and so reviews got farmed out to writers. Or someone has invented a GAN that writes good reviews, or at least a good first draft. I'd have to analyze the data to have more of an opinion. But yeah, verified purchaser means little.
The real question is, how economical it is for Amazon to really care about fake reviews? Buyer beware etc and there are more than enough scams running on Amazon / EBay / etc that I'm sure they're just treading water all the time. They have sued review writing outfits, so they care somewhat, but only after the problem got written up in enough newspapers... It is a hard job, trying to analyze all the data coming into their systems each day. I'm not sure any company has really implemented a lot of the research I read about in my literature survey.
reply