Slashdot Mirror
An App to Boil Down Online User Reviews
An anonymous reader writes "Is this a glimpse at the future of the Semantic Web? A new startup named Pluribo has developed a technology that can auto-summarize user reviews on the internet. It is a Firefox extension that can take a webpage filled with reviews and condense it down into a couple of sentences. Currently, it just works with Amazon electronics, but the potential seems incredible. Ars Technica took an in-depth look."
This is a serious reflection of our current times, where people's eyes gloss over if the concept at hand is not condensed into a convenient sound-byte.
I suppose you could call it the bleeding edge where complacency meets the loss of freedom and the fall of darkness where critical thought once stood.
Now there is enough probable demand to launch a startup designed to remove what minimal labor people are interested in dedicating to the quality of even their leisure time.
I'm sure many fantasize about strangling people this lazy/complacent, but honestly if they're unconscious enough not to care about their own toys, do they really possess a "life" for you to take from them?
VLC FOR MAC IS DYING! IF YOU DEVELOP, PLEASE SAVE IT!!
Well, you're not going to download a thousand product reviews in a couple of seconds, let alone summarize them. On the other hand, I would love to have this kind of functionality available on my own website, perhaps through a drupal module - a comment summary block would be dandy. Heck, you could even have summaries by tag - just summarize all the content tagged with "sco" for example, and find out that they are litigious bastards and that their unix sucked. I wonder if anyone is working on a Free/Open engine for this kind of thing.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
This sounds like the opposite of how to get useful information out of reviews, and more like the "consumer products" equivalent to the automatic resume scanner.
You know the resume scanners I'm talking about -- the ones that circular-file the candidate who took three years off work to get his Ph.D. in cognitive science (and whose thesis is a perfect fit for your business plan), preferring, instead, the guy who listed "20 years PROLOG, PL/1, BASIC, C, 10 years C++, 5 years Java, MCSE, A+", because obviously the second guy triggers more buzzwords. Because the HR drone won't understand any of the resumes, he/she just picks whichever one the scanner selects, and that's typically the one with the fewest career gaps and the most buzzwords. ("But that other Ph.D guy only has one or two languages, this guy has six! And that Ph.D guy's been out of work for three years, so obviously nobody would hire him!")
Ten reviews reading "Works. Fast, cheap, lightweight" and three reviews reading "Doesn't work" don't tell me anything, other than that the product might have reliability issues.
One review reading "Didn't work the first time. The manual doesn't mention that you have to make sure the jumper is in the correct position first, and then it works. I own an XYZ-123 and this new product was at least as fast, but at about half the price. Weighs about a pound." tells me everything I need to know -- that the three people who claimed it didn't work almost certainly didn't know how to configure it correctly, and that the first seven reviewers never had a problem because they weren't part of the edge case.
...or focus on a few outliers?
Yes, probably more than half the time actually, because 90% of the reviews are about as accurate as Slashdot comments, or as accurate as that percentage I just made up.
When it comes to hardware, I may work a bit better, however with the diversity of hardware that exists, that one comment that you missed saying "but don't EVER purchase this and install it if you have an [Insert Product]!" might be exactly what you need to know and the rest is just fluff. The same goes for a lot of software, and you might miss out on that "great find" by that one guy that said "its ok, but it's less efficient/configurable/easy and more glitchy/resource hog than [Product X]"
Comment removed based on user account deletion
Precisely: I like reading about the edge cases, because Joe Random is a freaking moron when it comes to electronics.
The whole "me too" effect is a huge part of today's marketing. That's why everyone and their mother wants a freaking iPod/iPhone.
-Billco, Fnarg.com
The idea behind the real world is that content providers will put bullshit in their tags, so that your hopelessly naive tools will instead create a fauxtlogy so that programs can easily duped into misleading customers to purchase worthless products.
The Semantic Web is an example of great ideas for doctoral theses that invariably end up being corrupted by greedy idiots, which is a classic marketing task.
Hello Farenheit 451. At least, that's what it sounds like to me. I don't know the exact quote, but it goes along the lines of; "There were so many novels, soon people just began reading the Reader's Digest version, just a snippet of all the classics. Soon that became too much, and so all that was left was flashy magazine articles." If someone can find the exact quote, that would be great.
That is what this article seems to me. It seems that people don't want to invest the time to actually learn or research something, and so they'd prefer the condensed version, the sound bytes, if you will.