Those reviews certainly seem pretty sketchy, and this sort of issue is definitely not unique to books.
What would be Amazon's best possible approach to dealing with this? Does there exist software good enough at distinguishing potentially fake reviews from real ones?
they should give more weight to the "verified purchase" reviews, I might even go as far as to say disallow reviews unless you actually bought the product, it would stop a lot of this, and the stupid review bandwagon that people seem to jump on
This. This more than anything. Amazon is now in a position not to need reviews from people that currently own that book. Or better still, there is a point where there is a verified purchases threshold that triggers the hiding of unverified votes.
Yes it still means a person can buy the book, then give it a bad review, then return it, however the effort to do this would be higher AND there would be a purchase pattern that begins to show itself.
You can easily detect that. If a person buys a lot of books and make a lot of 5 star or 1 star reviews, then returns them, that's clearly abuse and you ban them.
Or just wait until they have a lot of books and then reject every return. Their purchase history would tell a compelling story for the credit card bank.
These ARE verified purchases. You can buy them and just have to pay the reviewer for the purchase (or set the ebook to free for a limited time and let the reviewers download/"buy" the ebook in this timeframe). However, the strategy is not sustainable: Most 5 star reviews get "not helpful" marks and the ranking honors the number of purchases as well. The ebooks in question already get newer 1 star ratings and will take a nosedive when no new fake reviews are coming in.
Or perhaps remove non-verified reviews once there were more than just a couple of reviews.
I've never published a dishonest review, but I have reviewed a product or two that I bought somewhere else (not on Amazon), but I certainly "bought the product."
Isn't that why they have a did you find this review helpful button? That way bad reviews can be user flagged and given less weight. Of course that can be abused by spammers as well, so who knows how helpful it really is.
I wonder if Amazon has enough info to create a Googlesque filter bubble, so reviews are per user weighted to account for reviewer\user interest overlap.
What would be Amazon's best possible approach to dealing with this? Does there exist software good enough at distinguishing potentially fake reviews from real ones?