Most Active Stories
- Bradley Completes 'Grid' Of 4,000-Footers, Every Mountain In Every Month
- Dartmouth Once Again Weighing Value Of Greek Life On Campus
- How Kickstarter Kept A North Country Cafe Open - And Kept It In The Family
- Freezing Rain Causes Treacherous Roadways, Multiple Accidents
- Bill Would Require N.H. Employers To Offer Five Sick Days Per Year
Here's What's Awesome
Tue August 9, 2011
Fake Online Reviews Cower in Fear at New Fake-Detecting Software
Part of my job at NHPR is to moderate web comments. We get quite a few, so it takes time, but it's not too tough to spot spam, seeing as how real posters rarely post 701 times in a row about essay writing services.
The people who moderate online reviews have it much tougher - reviewers trying to sneak a fake positive or negative review of a business can be just subtle enough to make you think they're legit. Or maybe not, if new fake-detecting software from Cornell University pans out
The software showed that fake reviews are more like fiction than the real reviews they're designed to emulate, according to the researchers. In part, deceptive writers used more verbs than real review writers did, while the real writers used more punctuation than the deceptive writers. The deceptive writers also focused more on family and activities while the real writers focused more on the hotels themselves.
The software was about 90 percent accurate during its first test run - so if you were going to flood Yelp with fake reviews of this blog, well, you missed your chance. You'll have to be honest from here on out.
Now it's your turn. Share an awesome link or two in the comments - and we'll know if you don't really think the links are awesome.