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.
I did too! It's not hard to spot fake reviews!! I'll be sure to spot more in the future!
It's easy - fake reviews are overly-enthusiastic, and some of them go as far as to slam other brands. Real positive reviews are usually more sedate, little over-use of exclamation points!! and usually point out shortcomings of a product. Also, companies who astroturf usually submit multiple reviews, and it's usually posted in the same wording and typing style, which makes the fake reviews stick out even more. That's why when shopping for high ticket items I tend to read the negative reviews as well, and pay particular attention to longer reviews since fewer astroturfers invest the time in complete reviews.
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.
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.
They tested it on Slashdot's Packt book reviews!
I think you want the link for the paper, rather than the slides.
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.
FYI, The article is wrong, both are fake. Its in an article, duh. If it has too promotional of a tone, if there are buzzwords. If the spelling and grammar is too perfect.
Oh yeah...honest reviews of sufficient length always have unrelated details. Some promotional slob in an office somewhere isn't going to go off topic. Ya know, crap like "I treated my self to the Sopranos when I stayed there!". or "The maid was hot"
So, if you're like me, and into writing fake reviews...(yeah yeah, I know). don't capitalize, add useless details, and add criticisms no one would care about, like "I thought the hotel soap was a little fruity, but lucky I brought my own". Ya know.
The real path to male liberation
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.
I look for reviews that include both positives and negatives. Nothing is perfect, and most good reviewers will find at least one drawback or limitation in the object being reviewed. Reviews that are nothing but positives I don't give a lot of credit to - eve if they are real, they're probably not being objective.
I know anytime I write a review, I give a quick breakdown, hit the positives, hit the negatives, and close with a summary. (a lot of professional review sites, sites that review a large number of entrants in a particular field, do the same, look at for example independent hard drive reviews) I wish more others would do the same.
I work for the Department of Redundancy Department.
I've seen enough hentai to know where this is going.
Thanks. I was wondering why it didn't compile.
Anyone with an IQ over 100 can filter stuff. I was looking for a particular camera and all of the 'negative' reviews were people that expected it to come with more than a 32MB SD card or AA batteries. They were utterly crushed when their "christmas was ruined" because of these details. That or people that had a problem with Amazon and had no fault of the product itself.
There were a core group of middle of the pack reviews that touched on all the positives and negatives and then the praising reviews that may have been real, but gave no real information about the product. "CAME in 2 dAYS! Thanks amazon, can't wait to try this out!"
You want good reviews from people you received cash from to be declared fake by your algorithm? Don't quit your day job...
Seven puppies were harmed during the making of this post.
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?
Umm i believe that logic equation means if someone elses review is negative..and that product is made by a company whom paid the algorithm creator money...its default fake...duh. as in it only claims fake review so that the negative review is illegitamate? L2read:)
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.
Ship it anyway: We'll just buy some good buzz so it sells. You can fix it when the support calls come in.
Hugs and Kisses;
The Marketing Department
P.S. Your supervisor will be calling you shortly.
Any sufficiently advanced influence is indistinguishable from control.
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.
Now they have to make it to recognize fake profiles in dating sites (grin)
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).
It would be missing a colon in that case.
The equation in the original post says that, but the post he replied to (incorrectly) says the equation should be different.
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.
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.
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.
IT'S A TRAP!
my karma will be here long after I'm gone
Economics does not trump morality and ethics.
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.
It's interesting you point out well known issues in the original iPhone that you feel are 'fatal flaws' in one of the most successful single products on the market at the time. By extension of its success, I'd say those features are were significantly less important to a huge majority of Apple's target audience, and were in fact the minor and not the major flaws.
Now imagine that Apple's advertising agency had a number of astro-turfers out there specifically seeding those 'flaws' into general discussion along with some overriding positives. Those that latch onto these 'problems' as being significant to them are effectively no longer Apple's target market. Assuming that group is a small enough percentage, the rhetoric that is generated by the ensuing discussions is more likely to push their target demographic more strongly into a purchase. It also polarises a market that may have previously been sluggish to adopt new technologies.
If I see a review and the 'major problems' list a bunch of things that I don't care about. Not only does the review appear balanced, but it ends up in fact being overtly positive of the product, irrespective of how many 'stars' are given.
I see now. I misread "they" for "me", so I interpreted the joke from the perspective of lazy scientists instead of unscrupulous scientists. For instance, the following might be a lazy scientist's code:
if (review == positive && product_made_by == someone_they_received_cash_from)
Congratulations - you've outed yourself. You're who we're talking about. That wasn't hard. For your sake I hope this is a throwaway account. I've friended you here and I hope all my friends will too, so we can see the nonsense you post. Now that you're stuck in it, do you see the trap? In hindsight it should be obvious. Those were features iPhone lacked about a billion phones ago, when they faced competition that didn't have those features, or lacked other critical features iPhone did have. They're also features WP7 launched lacking that both iPhone and Android had when WP7 launched. You detected that and sensed you needed to defend your platform without understanding either the temporal context or who you're talking to. You lose. You're exactly who we're talking about. You know your job is to defend your platform, but you lack both context and art. You don't even mention WP7 in your post but by your derogatory remarks you hope to sway, and you can't because temporality prevents it.
When gas is four bucks a gallon fuel efficiency is going to move a lot of cars and American Muscle Cars are a premium item rather than a mass market item. If your job is to move Chevys then your job is to emphasize the luxury of the experience, not the cubic inches that burn fuel. When phones that alert you to who is calling by the ringtone MP3 you've associated with the caller is the standard form then phones that lack that feature are in the bargain bin and you need to draw focus on other things if moving those bargain bin phones is your job. It's not your job to point out that in years past different people focused on different things. To attempt to come to market with such a thing is a fool's game. That's not your fault because you're in Marketing rather than Engineering. The lack of the feature is an Engineering fail. But that you felt the need to come here in this context, reach so far to defend your product and not realize you're out of your depth, that's a Marketing fail. You guys really suck on every level. No wonder you're finding new lows in morale every quarter. Your final line's attempt to become reasonable isn't enough.
Now that you've burned this account for me, I may as well give you a little back. The whole "Apple is mindbending" thing isn't working. You know what? I don't aspire to Apple products and I'm not going to, but I would be flat stupid to try to pretend that others don't. I don't care for them because their Cathedral doesn't appeal to me. I prefer the Bazaar of Android. The others that do? I wouldn't alienate them by calling them stupid. They like different things than me. They have different needs is all. iProducts are good gear. I've walked around with an iPad, and complete strangers felt the need to strike up conversation and see the thing. Apple products just don't suit me because I demand to be the master of my gear. If you don't have that issue, they have iMovie and GarageBand, which is a great deal for what you get. I knew I was giving that up when I bought my Asus Transformer and I'm OK with that because it's got microSDHC, and it obeys me above all.
Do you see what you've done now? Do you have any clue at all? Is your supervisor looking on? Maybe he can explain it to you.
It's hilarious to watch you all fail so spectacularly and so predictably. Do you have any idea how entertaining your failure is? If not failing weren't so freaking obvious it wouldn't be as funny.
Help stamp out iliturcy.
That is why I look for the MOR reviews which it sounds like you do too. The ones that say its the greatest and the ones that say its a turd don't really give me any info so I look for the average Joe that you can tell by reading has used the thing.
For an example the review I read on Amazon for the Zoom bass pedal I ended up buying I found informative went like this: "Sounds are good as long as you don't go overboard with the effects, low noise but a few of the effects are just cheese, drum machine isn't gonna beat a dedicated machine but does keep a straight beat, whammy can be assigned to any effect. As long as you don't stomp the thing and try to use more than a couple of effects at a time it works good".
With that the guy gave me all I needed to know, don't go nuts with it, sound is decent as long as you don't overload the chips, and pedal is sturdy if not Doc Martin proof. He didn't act like it was the greatest nor garbage, just a nice general overview of what to expect. I bought the pedal and loved it.
So for me I've found just stick with the MOR and it all works out. If the review has tons of praise without any real nigglers? Most likely fake as anybody can find things they wish were different. By the same token those that find nothing but things wrong usually don't know how to use the thing and take their frustrations out on the review. So stick with the average guy MOR review and usually you're good to go.
ACs don't waste your time replying, your posts are never seen by me.
Dude, feel free to hate Apple. And hate me too if you want.
But, I have no affiliations with Apple, Microsoft, Google, etc, and I don't work in marketing or advertising.
Yeah, WM7 phones had the same issues at launch, but I used the original iPhone as a counter-example because history has shown that at the time it was incredibly successful despite those things that you claim are major flaws. Those were all issues that were regularly echoed in this forum and on many other internet blogs and boards. Yet, people still bought this new at the time product. Whether or not you or I think the product was any good, the original iPhone was an enormous marketing success.
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!!
Using the very same method, we could leverage moderation logs to predict which comments are informative, funny, deceptive...
Please admins, where's the API?
Delicious copypasta.
Contrary to the popular belief, there indeed is no God.
Exactly. Just read a bunch of reviews from different sources and it pretty easy to work out the real from the fake. I did get an A and Dux in media an marketing at school but don't hold that against me.
When looking at eBay buyers I don't spend much time on the positive reviews, I spend most of my time looking at the negative ones to get a better idea about the seller, mostly about how they handle dissatisfied customers. Oh and by not buying from the Asia region. Yeah yeah, its just that there are high levels of fraud there so I don't bother myself to mess around with it.
Except that some of the reviewers receive free merchandise to review as a part of that program that Amazon has for their top reviewers.
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.
"Anyone with an IQ over 100 can filter stuff."
That's not true: We have inherent unconscious bias (M.Gladwell, et. al.) and it's powerful enough to make us eat more food, buy more products, etc., because the "game" of selling to you capitalizes on your blindness, yes you (yourself) will have a subset of the human traits that make you a sheep to some marketing campaigns. Moo.
# (: There are two kinds of people in this world: You, who think youre immune from the science about human behavior ("Duh I filter all that stuff out") and me, who thinks that immunity lies in accepting my gullible side and avoiding the "marketing matrix."
Howto: Framing Your Thoughts: http://www.youtube.com/watch?v=5f9R9MtkpqM&feature=player_detailpage#t=222s
Yes, and those reviews are marked as being associated with the Amazon Vine program.
It's official. Most of you are morons.
Yes, but as long as the recipients of the free merch are duly noted, then there's enough transparency for me to make informed decisions.
You are welcome on my lawn.
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]
Agreed. I read positive/highly-ranked reviews for user information, negative reviews for true(r) user experience. I find that to be much more representative of whatever it is that's being reviewed.
When you sympathize with stupidity, you start thinking like an idiot.
Now you're posting as anonymous. Hehe!
Slashdot needs Geekcode | Can anyone recommend any good SCIFI? My tastes: Foundation, Startide Rising, CITY, Ringworld,