Comment by dougmccune | Hacker News Reader

Comment by dougmccune | Hacker News Reader

Anything with less than a real critical mass of reviews (less than hundreds) is way too easy to entirely game on Amazon. I wrote a book quite a few years ago on a niche tech topic. To be entirely honest, very few people read it. The positive reviews of the book were almost all from people I knew personally. Then the 1-star reviews started coming in. Each 1-star review had no actual content in the review. It was clear that the writers of these BS reviews hadn't read the book at all, since they didn't mention anything specific whatsoever. However, each of the 1-star reviews DID manage to mention a competing book that was "better". And all the bad reviews mentioned the same exact competing book. It was ridiculously obvious that someone was bashing my book to push a competing book instead, without any actual substance. At first I cared, and asked Amazon to remove the reviews, which they did. Then more BS reviews came back, I had them removed, they came back again, and eventually I just got tired and stopped caring.

How about leaving a 1-star review yourself to explain the spamming? Anyone considering to buy the book will not just look at the rating but also see what complaints people have (at least I do, to see if they mention something I would have a problem with).

I haven't really thought this through, so I'm open for arguments here.

That's actually a good idea, because you can vote on reviews on Amazon and it might become the 'most helpful negative review.'

That's awful. Has no one automated the process of checking for bogus reviews and reporting them?

How do you tell a bogus review from a real one, except by having it actually read by a human? This would be pretty expensive.

Expensive or not, Amazon has an obligation to make sure their review system has high integrity and is not "gamed" or no one will trust Amazon reviews anymore.

Not to mention the fact that pushing $3 spambooks that probably have high refund rates ahead of $30 expert guides in the rankings could and should lose Amazon money.

But these are all Kindle books which you can't request refunds for.

Reviews that all mention the same book, or even have little or no content, and have the same rating are suspicious and easily detectable by a trivial scan and compare against existing reviews. A harder problem is when the bogus review content becomes more "clever" (e.g. random rating differences, "entropy" in the content e.g. by misspellings, etc.).

Probably apply ML techniques. Similar to how spam is classified - build a classifier that determines the likelihood of a review being bogus, then flag it for human review if it exceeds a certain threshold.

They probably already have this, to be honest. Some of the fake reviews used keywords from the book title, probably in a learned attempt to game the classification.

Interestingly, Amazon can mine a great deal of the reviewers' histories to determine fake reviews. For example, a longtime customer of Amazon would get a higher "trustworthy" score for reviews than one who signed up 2 weeks ago.

Honestly, this should be no harder than spam classification

The good news is that you don't need to read all the books, because many bogus reviews tend to be written by the same "customers". Simply seeing a correlation of bad books getting good reviews, would result in those "customers" losing their ranking power from their reviews.

What's bad (really bad) here, is that not only are the books that are being ranked highly absolute crap, but they are crap in different categories. I.E. A "book" on swift, that was apparently "written", in a few hours, shoved onto Amazon, falsely ranked up - now ranks ahead of a 700 page opus on Perl, in the Perl category.

That's a total fail on Amazon's part, and really, really disappointing.

I don't find it at all surprising, however. Amazon can't even manage a half-decent search across the products they carry. I have this feeling that somewhere in Amazon, it has been decreed that the search and the rankings and everything else must be filtered through the same system that generates recommendations. You search for "4TB hard drive" and the 8th search result is a 3TB drive. Their site skips over much more relevant items apparently because the items are more strongly 'related' in terms of purchase history or browsing history or something. I expect exactly that kind of system is what is being gamed in these circumstances.

When it comes to reviews, the correct answer is that every user should have their tastes profiled and compared against the tastes of other users, with only users whose tastes in other areas counting strongly. I could easily imagine that this sort of thing might be difficult for Amazon to implement, though, depending on their infrastructure.

Amazon doesn't care about sellers. They simply don't. All they care about are customers. Don't be disappointed, as Amazon doesn't owe you anything.

Amazon Mechanical Turk?

In this case there were a few things that made it glaringly obvious (to a human at least).

The bogus reviews had one or more of these aspects:

- bad reviews from reviewers with no other reviews

- mentions of the same competing book in my bad reviews

- 5 star ratings of that mentioned competing book (and no other reviews beyond those)

- 1-star reviews of another random book. This one was interesting, there was another book (Service Oriented Architecture for Dummies) that is entirely unrelated. But 2 of the reviewers also gave shitty reviews to that book as well as mine. There's no logical reason that the same people badmouthing my book would have also read, reviewed, and badmouthed that other book (totally different topic) within a few days. So they were clearly hired for a number of books at once.

So yeah, you'd think some of those patterns would be easy to automatically detect. Although I assume it's constantly a game of cat and mouse.

I guess they could limit reviewing to accounts that have spent a decent chunk of cash and aggressively ban accounts that write fake reviews.

It's not automated but probably outsourced. Thus making it much harder to track.

Yelp has a system. It doesn't seem to be perfect; I've seen what looks like both false-negative and false-positive classification of fake reviews. But it seems to work decently well.

One thing I do like about their system is that you can click a link to read the reviews they consider "not recommended."

Here's what they say about it publicly: http://officialblog.yelp.com/2013/11/yelp-recommended-review...

Let me just say that Yelp's classification system is complete crap. Until a user starts actively using Yelp, their reviews get filtered out, which excludes most people who only post a review because they loved a certain business. Sometimes, five star reviews will vanish after months of being up, all because of a change in the algorithm. And the Yelp business team is extremely unresponsive when there is a clearly illegitimate review that needs to be removed, or really when there is any concern whatsoever.

This may not be the best place to bash Yelp, but if you're reading this, please don't pay Yelp for their exorbitantly-priced business service. It is absolute garbage.

Also it discourages any new people from participating. I signed up, posted a few reviews of businesses I'd been going to for years, then noticed they got filtered out and stopped participating.

And frankly, I don't have seem to have a lot of tastes in common with the hardcore Yelp users.

I reached this conclusion when the top two restaurants in a big city were a Mexican place and Greek food truck.

Heh, I actually agree with you (and emodendroket's) observation that Yelp buries reviews by new posters. (That's discouraged me from posting, too.)

Maybe I was too generous by saying their system works "decently well"; though I don't think I'd say "complete crap"--unless my business had been burned by fake bad reviews, which it sounds like happened to you.

Perhaps this illustrates how subtle/difficult this problem is.

It was only a matter of time before the review system was attacked, and they are losing.

From sponsored "impartial" reviews to niche items with way too many reviews and a mismatched helpful/not helpful or Q&A area, Amazon reviews are starting to lose their value.

I recently came across this[1] book, which was suggested to me after having purchased Randall Munroe's "What If?" xkcd book. At least this book is relatively up-front about what it is in its description, but it's clearly a blatant attempt to piggyback on the original book's success.

There are a few legitimate reviews that indicate this book doesn't really have much content, and then 2+ dozen fake 5-star reviews praising the book highly and saying how much better it is than Munroe's book. If you look at the review history for any of the 5-star reviewers, they all seem to be reviewing the same products, and often they are reviewing 3-5 books per day.

I reported the reviews via feedback, but never received a response. Ultimately it's just disappointing to see this kind of thing happening.

[1] http://amzn.com/1503234924

Wondering what your book was! I'm writing Linux for Hobbyists right now and wondering if it's a bit too niche.

It was Adobe Flex 3 for Dummies. Niche book on a tech topic that flamed out after a few years. If you've never written a book I'd still probably recommend doing it once. But don't expect to make any money, besides whatever advance you get. But it's still damn cool to be able to say you wrote a book.

Wow, that one's super niche haha!! Sure, I'm self-publishing. Just glad to say I'm an author and hoping to make a little bit of cash too, we'll see.

I always thought that technical book writing wasn't about making money directly, but for up selling in other areas.

I.e. improving your resume, looking prestigious to potential consulting clients, or landing paid speaking gigs.

This is correct. I was doing well in my career before the book, but it really took off after the book. However, I was already co-author of one book before that, and I blog prolifically, so that skews this.

The way it works is simple. Publishers hope to sell about 5,000 or so copies of your typical tech book. That's enough to keep the publisher going, but not enough to really make money for them. The publisher keeps those "filler" books going to keep up street cred and hopes to sometimes land the "killer" book that makes them a nice profit.

I can't share the sales info for my book, but let's just say that I think the book is doing better than one might expect for its category.

If you want to write a tech book, you want to go with O'Reillly. My advance was much larger than what O'Reilly would offer, but they sell more tech books in the long run. However, O'Reilly's Perl book section is saturated and they generally don't take new authors.

What I did to reposition my book was a strategy I wish more tech books would take: I focused on jobs. Instead of teaching every esoteric niche of a language (though I covered it well), I focused very heavily on skills that employers look for. I've been doing this for a long, long time and am very familiar with employer needs, so I was well-positioned to do this. That has led to my book doing better than expected: here's what you need for a job!

I now have a successful Perl consulting firm (http://www.allaroundtheworld.fr/) and that book, while I can't prove it helped, definitely didn't hurt.

Oh, and my publisher has spoken to an Amazon rep and a contact I have in Amazon tells me that they're aware of the situation and are looking into it. I don't have much hope, but who knows?

Reply on news.ycombinator.com