[AwesomeGriffin]

Perhaps some way that Yelp independently verifies the identity of the reviewer (maybe some two-factor authentication such as an SMS message), but keeps the reviewer's identity anonymous from the public to prevent harassment of honest reviewers.

This identity would also include some additional checks such as business affiliation and location, so for example a restaurant owner in a given zipcode can't post reviews on other restaurants within a certain radius of their business premises.

Not sure how scalable or workable all this would be though.

[hinkley]

While that would certainly stop Eddie down the street from posting 0 or 1 star reviews about my restaurant, you'd never be able to tell that he's started flooding the site with 2 star reviews to dilute me down from 3.7 stars to 3.4 so that his 3.5 star restaurant gets more foot traffic than I do.

[kbar13]

i'm not sure that having to provide PII to make a review is a good idea. Maybe if yelp is able to provide a kind of "reviewer's score" based on the reviewer's online activity then people will be more likely to trust reviews for being genuine.

[incongruity]

The key here is developing good points of convergent measures - not all of which would have to be valid for any one review to be weighted (think a Bayesian scoring approach?)

- Age of account

- Account engagement (patterns matter too)

- Check-ins via a mobile device at the business

- Check-ins at other near-by businesses (patterns matter too)

- Partner with a Credit Card company to offer Yelp-reward bucks to encourage reviews, track usage and validate reviews (and reviewers) [Use this to feed into the engagement score, above]

- Partner with OpenTable (they do this) & prompt reviews after attendance (they do this) – weight these reviews more heavily. [Use this to feed into the engagement score, above]

- Let me actually identify myself to Yelp or to the world (or to just business owners, ONLY if I want to [Use this to feed into the engagement score, above]

- Reviews of similar businesses (e.g.: I like thai food) -- patterns matter here. Do I rate all competitors poorly, etc? Did I post all reviews in one day, etc?

- Do my reviews vary significantly in a systematic way from others in a category? (This shouldn't be enough on its own, but variance might mean something)

- Do I post photos of the place? (Factor into engagement score, above -- but if it's only for one business, it might be a flag)

etc., etc.

Really – a statistical model shouldn't be that hard to do -- maybe processor intensive, but hard? It doesn't feel hard, given all the data they're sitting on...

[nerfhammer]

Work has been done on this. Apparently you can detect fake reviews to some degree using text features alone:

http://www.cs.uic.edu/~liub/FBS/fake-reviews.html

[derwiki]

I'm pretty sure the review filter (that everyone loves to hate) works this way.

[incongruity]

I've assumed it's something like that - but it shouldn't be too hard for them to be a little more forthcoming to explain their methodology a little bit without compromising the value of it.

[roadnottaken]

Yeah, what's to stop somebody from just lying about their business affiliations?

[jinushaun]

You don't need real identity verification to prevent fraud, you just need mods, which already exist (Elite) if only Yelp would get their head out of their ass and make Elite mods. They need a karma system. You need karma to write reviews that count towards the rating. I generally ignore reviews by people without friends. But in the current system, AFAIK, their vote still counts and it's the same as mine (Elite).

I feel like this self regulating system could work, just like fake profiles on Facebook don't work.