A few weeks ago I posted an article about the revelation that some big-name authors have been posting fake book reviews to give themselves a leg up. One of those exposed, R. J. Ellory, has apologized, and the book biz is still pretty steamed about it.
Newsweek magazine recently interviewed thriller writer Jeremy Duns, who did the research and exposed the scams. It was a lot of work.
But human eyes can go only so far. Fake reviews are ubiquitous on any site that lets users create anonymous accounts, such as Amazon, TripAdvisor, and Yelp; the tech research company Gartner projects that by 2014, between 10 percent and 15 percent of social-media reviews will be fake. Since Duns unmasked Ellory, he has been bombarded with requests to investigate other suspicious accounts; he began looking into one of them, a famous author, and gave up. “There were thousands of reviews. You’d need an algorithm to sort through them.”
You know about algorithms, right? Simply put, an algorithm is a step-by-step mathematical procedure to solve a problem. The folks at Facebook use algorithms to decide which ads to display or which of your friends’ statuses to show you (because you can’t be counted on to know this yourself).
Newsweek’s article tells us the same methods are being used by researchers at Cornell University to detect fake hotel reviews on TripAdvisor. I’ve often read reviews here about a place or hotel or restaurant—both positive and negative—and have my own method of weeding out the losers, having to do with throwing out the high and low scores and … well, you get the idea. (Actually, I assume that for anything involving customer service, some negative reviews have to do with either the server or the served having a bad day or a personality conflict. Those I overlook, particularly when the majority of the reviews are positive.)
The Cornell algorithm isolates linguistic differences between real and fake reviews. I also have my own ideas about determining real and fake: when I read a one-star book review with the words Did other reviewers read the same book as I did? I won’t be buying that book. And I assume 90 percent of the five-star reviews are friends and fam, so I ignore those too. 🙂
Nonetheless, I’m rooting for something scientific to save me from the gushers, the whiners … and the gamers. Stop it, y’all.
Disclosure of Material Connection: I have not received any compensation for writing this post. I have no material connection to the brands, products, or services that I have mentioned. I am disclosing this in accordance with the Federal Trade Commission’s 16 CFR, Part 255: “Guides Concerning the Use of Endorsements and Testimonials in Advertising.”