HN Gopher Feed (2017-12-30) - page 1 of 10
Fakespot - measure the legitimacy of reviews on popular sites
49 points by throwaway13337https://www.fakespot.com/
pavel_lishin - 2 hours ago
How do fake reviewers get the "verified purchase" tag on Amazon?
This particular analysis explicitly lists "Alex Brown" as a
"Unreliable Reviewer", but the Amazon page says his review is a
verified purchase.Did Novopal just buy it for him?(Also, I wish I
could plug my Amazon profile into Fakespot and see what it thinks
about me.): https://www.fakespot.com/product/novopal-baby-
pkaye - 2 hours ago
The fake reviewer will buy the product first and then the company
will reimburse and reward the reviewer on the side once a review
pglhn - 2 hours ago
I've heard that one way of doing this is for the seller to give
the purchaser a discount coupon for 100% off
achamayou - 1 hours ago
> Also, I wish I could plug my Amazon profile into Fakespot and
see what it thinks about meAlthough that sounds neat, and I wish
I could do that too, I suspect this would be far too helpful to
actors running bogus profiles to be allowed to exist.
forapurpose - 2 hours ago
I wonder how they address this problem, which affects all attempts
to spot fake reviews: How do they know how accurate their results
are? What are the false negative and false positive rates? To
measure your accuracy objectively, you'd need an independent method
to verify, with high reliability, the legitimacy of the reviews.
(You may think you can spot them manually, and maybe you can spot
some obvious ones, but false negatives are perilous: You don't know
if the reviewer is simply better at hiding their trick than you are
in discovering it - and they likely have far more expertise and
experience than you do. Consider: Could you write a fake review
that would trick someone like yourself?)Fakespot's FAQ says the
following. I think the use of machine learning is a good example of
the problem: The machine needs a good data set from which to learn,
which means they'd have to flag reviews in the training data as
legitimate or not - but they have no way to determine that.
Basically, they are training the machine to make the same
judgments, of unknown, accuracy, as the humans (in fairness, I'm
making some presumptions about their use of machine learning).What
criteria are used by Fakespot when analyzing reviews?Fakespot
utilizes numerous technologies to validate the authenticity of
reviews.The primary criteria is the language utilized by the
reviewer, the profile of the reviewer,correlation with other
reviewers data and machine learning algorithm that focuses on
improving itself by detecting fraudulent reviews.The technologies
include: profile clusters, sentiment analysis, cluster correlation
and artificial intelligence intertwined with these
functionalities.https://www.fakespot.com/faq As Richard Feynman
said, "The first principle is that you must not fool yourself --
and you are the easiest person to fool."
mehrdadn - 2 hours ago
Does anyone know how well it works to just check to see if reviews
have been posted in a short/bursty duration? I feel like most fake
ones seem to be ones posted very recently or during a short time
period, but I'm not sure if that just means I'm missing the rest of
them or not.
mehrdadn - 2 hours ago
I'm skeptical Fakespot works well. Consider this product:>
https://www.amazon.com/gp/product/B0064EKNKIWhere do they get the
idea that 25% of the reviews are unreliable/deceptive? I bought it
and it works just fine, which is pretty consistent with 87% of the
reviews being 4+. Why should I think otherwise?
Zak - 1 hours ago
It's attempting to spot sponsored reviews, not bad products.
mehrdadn - 1 hours ago
To quote itself, it's spotting "unreliable" and "deceptive"
reviews, not merely sponsored ones. And even in the latter
case: do those look like sponsored reviews?
Zak - 1 hours ago
No, but I imagine sponsored reviews aren't supposed to look
like sponsored reviews.The three it flagged as suspicious for
the ethernet cable above were all very short, like "Great
product!" or "A++++". I'm not sure what to think of that. I
write reviews (of flashlights) as a hobby and wouldn't call
something that doesn't describe how the product was tested or
include any technical or performance analysis a review.On the
other hand, the average buyer doesn't usually have the
knowledge to write a useful technical review and just wants
to report that the product met their expectations.
abawany - 1 hours ago
I looked at the critical reviews and it seems that there was an
uptick of fake products sent to customers. Perhaps such an uptick
triggers this fakespot behavior? My observation for this and
other products is that when something is shady, the reviews
consist of a lot of date-clustered reviews that are positive
followed by a trickle of critical reviews that seem to point out
specific issues with the product.
zionic - 1 hours ago
I really can't stand this website.We had them say ~40% of our
Amazon reviews were fake/unreliable... and I'm pretty damn sure
we'd know if we were faking our own reviews.I don't know how their
system works, but the false positive rate in my experience is
nikanj - 1 hours ago
Their long-term monetization strategy probably involves you
paying them to ?verify? your reviews.
zzzcpan - 1 hours ago
Let's be honest, fake reviews is a fake problem. Reviews were never
supposed to work for customers' benefits. I mean how in the world
shallow emotional opinions of people with unmet expectations and
wasted time or with fanatic love for the brand would help anyone?
It's just that when people start ignoring reviews all those
corporations don't make as much profits.
bluetwo - 58 minutes ago
I wish this site worked well. Based on my tests it doesn't. This is
a real problem without yet a solution.