Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Fake Amazon Tech Book Reviews Are Hurting My Book

blogs.perl.org

Post reply on HN
Print view View original

31–40 of 124 posts

Re: Fake Amazon Tech Book Reviews Are Hurting My Book

#31

Post by hurin »

Ovid wrote: post #23
rcthompson wrote: post #20

In light of that recent article about computer-generated prose being in many cases indistinguishable from human-written, I'd say those fake reviews are likely written by a computer. Notice that they're mostly of the form "I didn't think I'd be interested in [TOPIC] but [TITLE] was really interesting and really helped me learn about [TOPIC]."

That's an interesting thought. I'm pretty sure I could write up a nice grammar to chunk out "interesting" reviews of books. Instead of whining about my book getting buried by fake reviews, maybe I should chuck it and cache in on said reviews!

There should be very obvious ways to identify "review bots" - especially given that reviews are tied to an amazon accounts purchase and browsing history.

That they don't have an efficient algorithm for this sounds more like they don't really care and never bothered with it.

Re: Fake Amazon Tech Book Reviews Are Hurting My Book

#32

Post by obsurveyor »

theVirginian wrote: post #28
jplahn wrote: post #12

I wonder if any NLP approaches could yield an improvement on this? I immediately think of doing some NER on the review (looking for the title, authors, chapters, even specific topics) and if none of the above are mentioned, or at least not mentioned "enough", then it can be flagged for review as potential spam. Likewise, if you did sentiment analysis on a 5 star review, but the sentiment was either neutral or negativ…

I would say just include a code inside the box that you can type in to validate your review as an actual purchaser. Then Amazon could heavily weight these reviews, at least for products known to be prone to scam reviews.

They already have a system for this: "Amazon Verified Purchase" will appear below the title of a review from someone who bought the book. Of course, they had to have purchased it from Amazon. They could default to only showing verified reviews by default or weighting verified reviews higher than unverified ones. It's too easy to create accounts and reviews to keep letting this just slide.

Re: Fake Amazon Tech Book Reviews Are Hurting My Book

#33

Post by impostervt »

dublinben wrote: post #30
impostervt wrote: post #3

Web cache version, since the site is down for me: http://webcache.googleusercontent.com/search?q=cache:blogs.p... While not really related, I seem to run across a lot of books on Amazon that have a high number of 5 star reviews that, upon reading, are just bad. Seems to happen a lot with books by independent sci-fi authors with Kindle-only books... Of course, "bad" is just my opinion.

Do you leave your own review on those books to counteract the unearned rating?

Usually yes, but always. I wish Amazon let you just give a star rating, instead of requiring you to add a real comment.

Re: Fake Amazon Tech Book Reviews Are Hurting My Book

#34

Post by scrabble »

dougmccune wrote: post #15

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

Re: Fake Amazon Tech Book Reviews Are Hurting My Book

#35

Post by tracker1 »

impostervt wrote: post #3

Web cache version, since the site is down for me: http://webcache.googleusercontent.com/search?q=cache:blogs.p... While not really related, I seem to run across a lot of books on Amazon that have a high number of 5 star reviews that, upon reading, are just bad. Seems to happen a lot with books by independent sci-fi authors with Kindle-only books... Of course, "bad" is just my opinion.

I've taken to looking at reviewer's "other" reviews when I see a slew of 1 or 5-star reviews for anything... It becomes pretty obvious which ones are real, or fake.

I've come to trust those items with all 4-5 star reviews far less than I used to.

Re: Fake Amazon Tech Book Reviews Are Hurting My Book

#36

Post by jessaustin »

vhost- wrote: post #18
awjr wrote: post #14

Earlier quoted context omitted.

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…

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.

Re: Fake Amazon Tech Book Reviews Are Hurting My Book

#37

Post by nine_k »

scrabble wrote: post #34
dougmccune wrote: post #15

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'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.

Re: Fake Amazon Tech Book Reviews Are Hurting My Book

#38

Post by echoless »

MayanAstronaut wrote: post #29

Much like search engines combat black hat SEO, amazon and reviews systems can do the same. It would not be to hard too for amazon. Use reviews that are a 'Verified Purchase' and highly 'helpful' reviews as a training/test set. Then machine learn a weighting to every review based on the (product, reviewer, other reviews, etc features...) The outcome could actually hinder tactics like this for products that game the sy…

It's always a cat and mouse game however. Once they employ machine learning, I'm assuming the spammers will adapt and create reviews that fool the algorithm(though at an increased initial cost).

Re: Fake Amazon Tech Book Reviews Are Hurting My Book

#40

Post by tracker1 »

hurin wrote: post #31
Ovid wrote: post #23

Earlier quoted context omitted.

That's an interesting thought. I'm pretty sure I could write up a nice grammar to chunk out "interesting" reviews of books. Instead of whining about my book getting buried by fake reviews, maybe I should chuck it and cache in on said reviews!

There should be very obvious ways to identify "review bots" - especially given that reviews are tied to an amazon accounts purchase and browsing history. That they don't have an efficient algorithm for this sounds more like they don't really care and never bothered with it.

I'd say it's more likely that this is a complex problem, and will take a bit of time and computing power to work through...

Amazon has hundreds of thousands of products with tens of millions of reviews... correlating that with log history for each review will take a lot of time... not just to run, but to write any automated process, and work through resolving it.

It seems to me that Amazon seems to be pretty responsive when bot reviews are pointed out, and that may be, or at least have been a more effective strategy... But looking at an article a few days ago regarding twitter bot nets, and even seeing them try to draw me in... it's a very large problem all around.

Bad people will do bad things... as will misguided people. The bigger issue is the false positives... we've all read the horror stories of when a legitimate domain gets screwed by (insert popular domain registrar here) because of incorrect reportiong/reaction... or when a business' google apps is offline, and nobody can be reached at google... it happens.

In the case mentioned in TFA... it's probably prudent to ban the publisher in question. In others, the case may well be different.

Post reply on HN