Slashdot Mirror
Cornell Software Fingers Fake Online Reviews
Eric Smalley writes "If you're like most people, you give yourself high ratings when it comes to figuring out when someone's trying to con you. Problem is, most people aren't actually good at it — at least as far as detecting fake positive consumer reviews. Fortunately, technology is poised to make up for this all-too-human failing. Cornell University researchers have developed software that they say can detect fake reviews (PDF)."
This topic is TOPS! It is a beautiful summary!!! I highly recommend it!!!
The Christian Right is Neither (Christian nor right). See: Matthew 23, Matthew 25, Ezekiel 16:48-50
They also gave hints on how to defeat it.
if (review == negative && product_made_by == someone_we_received_cash_from)
review_fake = true
I prefer searching for negative reviews to find out what kind of problems or weak points I can expect. Then I can see whether the product has any real flaws (or whether the reviews were just written by idiots who cannot unpack/install/operate the thing). All the positives are already presented by the producer, anyway.
I picked out the fake review immediately.
-mrxak
Onions Will Kill You
good, I'll use it on the crappy book reviews/ads prevalent on this site.
It's an "undecidable" problem. Think for a moment how you'd define "fake".
Fuck systemd. Fuck Redhat. Fuck Soylent, too. Wait, scratch the last one.
As soon as I walked down the street holding a print-out of this PDF research paper, women were immediately attracted to me.
They tested it on Slashdot's Packt book reviews!
I think you want the link for the paper, rather than the slides.
Q: How do you tell a review is fake?
A: There's text on the screen.
If this catches on it will just make the fake-reviewers work harder, but it won't, by itself, stop them.
Reputation-based reviews are probably coming. Of course, it's possible to create a fake reputation if you plan ahead of time.
Knowledge is how to play a game, intelligence is how to win, wisdom is knowing what game to play.
The bubbly-over-the-top sound of the review on the right screamed "this is not the opinion of a person exercising sober judgment."
So, even if it wasn't a fake it wouldn't be useful.
The one on the right is formulaic enough that it *could* be fake, so I would need to rely on the reputation of the author or publisher. If I saw it in a major newspaper's web site with a byline of a newspaper employee or a reputable wire service, I would assume it was legit. If I found it on some random blog or a web site where anyone can post anything, I wouldn't be as likely give it the benefit of the doubt unless the author had a good reputation.
Knowledge is how to play a game, intelligence is how to win, wisdom is knowing what game to play.
you get caught we cut your head off mount it on a pike and take pics and send to all marketing companies world wide.
PROBLEM WILL then solve.....
This is why I look at the negative reviews first to see if there are any particularly frequent problems with the product.
Of course, a few years ago when I was apartment shopping online, I found that this tactic doesn't always work so well. On one side, you have the management companies posting shill positive reviews for their apartments, and on the other side, you have disgruntled evicted tenants posting overblown negative reviews for those apartments.
if (book_publisher == Packt && book_reviewer == RickJWagner)
{
shill_review = true;
}
I've seen enough hentai to know where this is going.
...through her pretty pink panties.
Seriously, that headline is a little quizzical. A split-second after I got my mind out of the gutter, for half a moment I was under the impression that this was an article about simulations of robotic fingers literally (or would that be virtually?) pointing at advertisements.
I write fake reviews, and I really appreciate all of your pointers on what you see in a fake review. We usually have 2 to 3 people writing reviews on a product at a time so writing styles don't repeat. We also sometimes write negative reviews on competitor products, but that's done "under the table," as they say. It's not encouraged officially, but it's certainly not prohibited. Managers do see these from time to time, though; and I think it improves your status here. Marketing is a pretty cut throat business.
There are, what took you a few minutes to write into a post has been a staple of astroturfing and smear PR for years. Have you seen the stories about Google having bad privacy with the 1st comment on slashdot reading exactly like you just described? They have subsided as of late (maybe because Google+ is generating so much news both good and bad they dont need to) but I'm sure they will be back. They are paid and persistent. Dont believe me? Facebook admitted they were doing this. Hired the same PR firm as MS. MS is an investor in FB. Look it up -- be informed.
its *ALL* fake. Either pissed off people or paid supports.
---- Booth was a patriot ----
and on the other side, you have disgruntled evicted tenants posting overblown negative reviews for those apartments.
All they do is gripe about crappy Windows.
Have gnu, will travel.
... what we know is that this is just another form of information security.
The people who produce false reviews will develop a tool that not only fakes the reviews, but then applies this exact software (in the article) to analyze it, and then provides logical adjustments until this exact software cannot discern the difference between the adjusted outcome or real reviews.
All these cold wars suck. A little honesty and integrity in the world would be great, but when capitalism pits us against each other to survive (not for wants, but for needs), this is exactly what you should expect. I prefer cooperation over competition, when it comes to survival, but if the social environment dictates that I must do bad to survive, I must survive.
If you respond, please don't be the shallow minded bum that thinks there isn't a causal relationship between what I just said and how people fake reviews (for revenue).
I want to see how it does on reviews of the Steering Wheel Desk http://www.amazon.com/Wheelmate-Laptop-Steering-Wheel-Desk/dp/B000IZGIA8/ref=sr_1_1?ie=UTF8&qid=1311732433&sr=8-1
This is Spam! Citi, on behalf of Sears, has decided to spam me daily with notifications of my balance due. This despite my "opt-in" to be to be notified monthly and the fact that my "opt-in" request was working "once a month" until last week. And, No. I am not overdue, late, in arrears or in any other negative Citi space! I did bring this spam to Citi's attention. They replied that my email was forwarded to "someone who doesn't give a flying fuck" although, not in so many words! And, the next "higher-up the food chainer" hasn't replied with substantive apologies or solutions at all. As usual, Citi doesn't give a flying fuck about the individual. I shall have to report this as Spam and hope they hit the SORBS list. Please, use "Spamgrabber" with your Outlook 2007/10 email client and report ALL Spam from your financial institutions. Who cares if it isn't clearly Spam? Just use the principle of "Balanced Reciprocity"! I have no idea, for those using other email clients, how you easily report Spam without an add-in like this ??.
May the lies we live by make us strong, healthy, happy and wise - Kurt Vonnegut.
I like the idea very much. The article showed an example of two comments: one on the left and one on the right. This example is only easily spotted for folks familiar with SEO and web dev stuff. The review on the right hand side was clearly spam because the name of the product was used several times in the comment to pad a search engine. My guess is that, for a laymen, it isn't that obvious. Signs to look for are: (1) excessive use of capitol letters and punctuation marks, (2) excessive use of the product/service name, (3) Excessive grammar errors (can indicate a user paid to post but not necessarily so.), and (4) reviews that appear to be almost identical between products with simply the name switched out which could indicate a script doing the review.
When I shop at newegg.ca the reviews can also be by verified owners, who actually bought the product. I tend to check off that when looking at reviews. Everything else is fluff.
Flawless astroturf is indistinguishable from hard work. It's certainly possible, but is it actually cheaper than not making a crap product in the first place? The makers of flawless astroturf are unlikely to be employed by Motel 69. I've heard it presently costs somewhere north of $500m to get a new drug approved by the FDA. The dreadnoughts of Amazonia are overstated.
I've argued several times recently for the virtues of pseudonymous pluripotency and against the consolidated identity of Google+. But then, I don't besmirch my pseudonymous splendour with motel reviews. (I fear my gig could be busted on a measure of bifurcated alliteration; but for the moment, writing such a filter is--you guessed it--indistinguishable from hard work.)
When you think about it, this is the Turing test in miniature. In the samples given, the straight man on the left is the easier text type to mimic flawlessly than the gusher on the right; the difference is that the gushy cake mix is more likely (I presume) to influence consumers with poor impulse control, so the fakers helped themselves to a giant box of Woody Allen instant pudding.
I picked both samples as fake. The sample on the left doesn't pass for anything more clever than a really long paper tape with heart-felt opinions on infinite spools; the sample on the right doesn't pass any test.
The last book I purchased with recourse to the Amazon rabble was The Elements of Statistical Learning.
The review that finally sold me was the guy who said, "whenever I get into real trouble, this is the first book I crack open". He was saying that there was plenty of depth between the lines, for the reader willing to struggle. Any large book I'm going to lug around in the physical world had better come equipped with more lifelines than the 2nd Titanic.
I also bought an introduction to VHDL programming at the same time (Amazon now has me narrowed down to a few dozen meatspace puppets) that was precisely the opposite: a quick bootstrap with nothing whatsoever to recommend a third reading. For the price, I was disappointed. Perhaps it paid for itself on the first reading; even if it did, it was a soulless experience.
It's not that everyone wants convenience. It's more the case that most large companies want consumers who want convenience. Convenience is a sound people make while opening their wallets knowing that they skipped out on proper evaluation.
Competence is indistinguishable from hard work. When I do read reviews, I tend to scan *every* review, not just the five (most helpful to Amazon) that they offer up for one click less. While my eyes are skimming madly for dialtone in the morass of pseudo-babble, my brain is consolidating in background the few useful sentences, pro against con. The brain is good at PCA if you give it a chance.
Don't believe everything you read on the Internet. Not even this.
Help stamp out iliturcy.
Are fake as well. There are very few shows that don't get their products to review directly from the manufacturer. Most only get the products if they give a positive review. Did you ever watch a car show that didn't praise a car? How many shows actually compare products they bought in shops themselves and aren't afraid to fail the lot?
I was promised a flying car. Where is my flying car?
Apparently quite well – I’ve checked a few reviews on the product and all three people gave it 5 stars and called it AWESOME!!
How do they know the control group is authentic? There is nothing remotely specific in the left one. It says noob shill all over. Who would honestly submit a review like that and think it will be helpful to others?
Also funny how they call the fake ones "deceptive" and the ones supposedly written by customers "truthful". As if real customers wouldn't deceive or misperceive.
Using the very same method, we could leverage moderation logs to predict which comments are informative, funny, deceptive...
Please admins, where's the API?
I think that post pretty much encapsulates the political process in any democracy.
Trash the apples in your opponent's plan and present the oranges of your own plan as apples.
Can they build one to see if my wife is faking?
Agree. Also, there are too many reviews by people who have only used their product for less than a week, and YOU CAN'T TELL WHICH ONE THESE ARE (unless they state so). "I've played with this thing for one whole day now! FIVE STARS!!!!"
I would much rather have reviews from people who have used the thing for 3 months, to see if there are any late-showing quirks, batteries that fail after a few weeks, fragile components, customer support issues, etc.
404555974007725459910684486621289147856453481154 in hex is "You sank my Battleship?"
[GPG key in journal]