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
What about fake reviews that are posted by the competition. I have a hard time believing that anybody that is posting fake reviews of their products isn't doing that for their competition as well.
Ultimately, I tend to look for the reviews that are the most informative, things that look plausible and give me more information than what's in the listing. Usually those are fairly reliable as they're harder to fake. Not that it's a perfect system, but it is more time consuming to post a review like that since you really have to do different ones for different sites.
I think you want the link for the paper, rather than the slides.
If I was being to paid to astroturf a product, I'd prepare a number of generally positive and a few 'negative' reviews that pointed out a few flaws in the product. Of course those would only be flaws that the majority of people will either not care about, or will see as positive to themselves. The idea is to seed a small element of trust in the product, and take away the feeling of blind risk from the potential customer.
In some of those reviews I'd also mention another product or two that I felt were 'better', again only in some specific way that most people wouldn't care about. This seeds an element of legitimacy to the product, especially when comparing it against known good competition. The idea is not to get 100% of people thinking your product is the best, but to catch a large number of customers that would have otherwise never even considered your product.
The third sneaky thing that I'd do would be to review a competing product or two with a very minor mention of the product I'm being paid to astroturf. In that review I'd be generally positive, while at the same time throwing in a few questions that seeded some doubt and uncertainty about some seemingly important aspect of the competitor's product that my actual product reviews (and legitimate advertisements) had covered as being fully supported. In this way, the person 'researching' the general class of product is likely to do some further research into 'my' products - specifically searching for these 'missing' or 'doubtful' aspects that I've alluded to.
The above tactics are readily seen across the board in general advertisements where a company will harp on about some new 'feature' that they have - especially a feature that competing products don't officially advertise or mention - thus implying that the feature does not (or may not) exist in those other products. In reality the feature is a straw man style argument that compares apples/oranges in a way that less than 10% of the potential market would see as an invalid or incomplete comparison.
How does anyone know that there aren't people out there readily using any or all of the above tactics?
Not the GP here, different AC who mostly agrees with him. I also agree with you re: informative stuff. Both filters are useful alone, better in concert.
What about fake reviews that are posted by the competition. I have a hard time believing that anybody that is posting fake reviews of their products isn't doing that for their competition as well.
It's simple economics. You spend your review-spamming money where you get the best ROI.
If I post a positive review for my product, I get all the gains, while the loss of sales is distributed over all my competitors _and_ the null competitor, (i.e. people who wouldn't have purchased anything but for my review).
If I post a single negative review to a competitor, he takes all the loss, while the gains are distributed over all my other competitors and me and the null competitor (people who would have bought from my competitor, but now don't buy at all).
So in a case where there's me and one other competitor, and assuming equal influence of positive and negative reviews, positive reviews are slightly better (because they pull customers in, rather than putting them off entirely). Equal influence is bullshit. of course; if my competitor is larger, a negative review there will be seen by more people, so more effective, and many people do have a skeptical bias (as recommended by GP and seconded by me), so negative reviews will have more influence. This means in a two-seller market, negative reviewing likely is viable.
Still, if there's a "sufficient" number of competitors (depending on exact influence levels), I'm obviously going to see much more benefit per review from positively reviewing my own than negatively reviewing competitors. Now there's diminishing returns with more fake reviews for myself, so at some point a negative campaign will be better ROI than further expansion of my positive campaign; I personally suspect other advertising techniques will have better ROI, so you'll likely never get to that point, but that's just a hunch. I wouldn't go as far as to suggest negative reviewing has negative ROI, so it's still quite possible if you have ridiculous advertising budget and have exhausted all higher-ROI approaches, it's just not prevalent in practice.
That's why I appreciate Amazon's "verified purchaser" or whatever it's called. When a review is posted by someone who actually bought the product from Amazon, it shows up beneath the title of the review. By only looking at those, I'm able to eliminate a lot of the junk reviews. Now, nothing stops the competition from actually buying the product and then trashing it, but I can also look up other reviews by that reviewer. This gives me very good insight into the way that person thinks.
I suppose nothing stops a phony from creating an Amazon review, buying a bunch of products and then buying the product he intends to trash with a bad review. But I figure that's not really likely. And I could probably figure it out by reading their previous reviews anyway.
You are welcome on my lawn.
... 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).
These are effective strategies that have been in use and working for some time. There are a few refinements the past decade. People often skip the middle of the review or zone out in the middle. So when you're 'turfing a product with fatal flaws like for example a phone that can't multitask, has no apps and can't even set your "I like big butts" MP3 as a ringtone for your amply so endowed love interest like other phones can, that's a good spot to pretend those slights don't exist and instead go on about some minor flaw that absolutely nobody could care about before dismissing it as a minor issue not worthy of subtracting a star.
For the most part they've given up using the ESL contingent from Bangalore and Costa Rica for the astroturfing campaigns. They gave a lot of column inch per dollar, but just weren't persuasive. They couldn't tell when they were being played, they weren't aware of context. They would just argue away, pasting their talking points into a dialog with someone who understood what was going on without a care how it looked to the audience in general. The new ones would just paste the script verbatim as if it was a trump card and blow everybody else's chance at subtlety. It was a negative return on investment. It took so much more investment in psych majors to build up decent arguments than the 'turfers cost to post them, and then the 'turfers just ruined it with poor delivery. So now they just hire the psych majors I think. And prisoners. Lots of Arizona prisoners.
I think they're investing more in poisoning before. If a venue isn't generally supportive they might spend some considerable effort making the entire site unsavory, or picking apart established players in order to diminish their interest in the site. Griefer is probably the most advanced form of 'turfer out there today - and I don't mean goatse guy - he's a legitimate researcher into captcha defeat technologies.
There are even absurd parodies of fans of products in play. They gush adoration for minor features at every opportunity but never mention prime benefits and dismiss (but never fail to mention) major shortcomings as trivial. They creatively destroy their credibility with every post to create a positive impression of what they criticize and a negative impression of what they praise. They're the marketing version of getting your idiot cousin on your competitor's payroll. This rabbit hole goes much further than you've considered.
Help stamp out iliturcy.
Apparently quite well – I’ve checked a few reviews on the product and all three people gave it 5 stars and called it AWESOME!!