BooRah is a semantic and natural language processing aggregator of restaurant reviews. The service pulls in reviews from numerous review sites and a substantial list of restaurant review blogs, then analyzes the emotional tone of the reviews it finds. Good reviews ("Rahs") and bad reviews ("Boohs") are collected concerning food, service and ambience.
It's a small but interesting site and the basic premise here is something that could be expanded beyond restaurants alone, something the company says it intends to do. I like it a lot.
Headquartered in Mountain View, CA, the company launched with information gleaned from over a half million online restaurant reviews in San Francisco, Los Angeles and New York. Last week it expanded to include a total of 20 cites, though information can be found on the site about restaurants almost anywhere in the US and in some cities internationally. The company is adding in-depth coverage of about 1 city a week it says and is now powering restaurant reviews on the directory site AmericanTowns.
BooRah uses affiliate services to display menus, make reservations and offer big discounts for restaurants in a long list of cities. These added features are a very nice touch, especially the menu display from AllMenus.com.
The reviews that get processed are identified by semantic analysis identifying food blogs among 100,000 blogs being indexed. That number could be bigger, but it's unclear what percentage of those indexed blogs are in fact food blogs.
Inside the review excerpts you'll find food terms, like a particular dish, identified and linked out to a search results page displaying that same item in the same location you're currently looking at. That's really nice, so if I'm reading a review that says some place's dolmas are alright but aren't the best in town - I'm one click on the word dolmas away from finding out where in town is said to have better ones. Yelp lets you search for terms in a city of course, but making it one click automatically is nice.
I wrote a review this morning and the parsing is a little funky. The key term in my review is "raw," which should be discernible since the culinary category is "organic." Instead, BooRah pulls out a link to "cooked stuff" for searching. That's the opposite of what a user would want in this, admittedly niche case. Food, like many other niche topics, needs strong long-tail analysis - doesn't it? Maybe it's unrealistic to expect semantic analysis to be strong in outlying, long-tail use cases - perhaps full text search ala Google is going to serve said user better. I hope not, though.
Yelp doesn't do a lot of what BooRah does. The final bit of semantics I found on the site was a "semantic cloud" for selected cities. That gives you a good idea what kinds of foods and issues people are talking the most about for a given location and lets you click through to read those reviews.
The site searches for reviews across a lot of different sources, depending on the location. Yelp is not included, which is a real shame, but sites like CitySearch, Yahoo Travel, Tripadvisor and many more are included. In some locations the local newspaper website is included in review sources. You can easily filter between sources or chose to just look at food review blogs.
Reviews can also be written on the BooRah site itself. When you sign up for an account you're prompted to select between 3 different charities, presumably ad revenue you generate will be shared with those charities. That's a nice touch. I don't see Yelp doing that, do you?
RSS feeds for new reviews of restaurants in a particular city? I'll subscribe to that! I'd like to have some more granular control of such a feed: new reviews, new restaurants or new restaurants with 3 or more reviews. Yelp has pretty limited RSS feeds.
Finally, the Boos and the Rah's are probably the biggest differentiator here. It is hard for systems like this to recognize things like sarcasm or other peculiarities of human communication - but BooRah seems to be doing a fairly good job in the little bit that I looked around it. I really like the way it pulls out emotive quotes from reviews. My initial skepticism has subsided, but I'll be keeping a close eye on this feature as I use the site more.
Seeing positive and negative reviews around three different parts of a restaurant (food, service and ambience) really is far better than just seeing a number of stars. This method of displaying reviews scales for the individual user, far better than stars and full text reviews do.
The Down Sides
BooRah has been around for a little while but it still feels like its database could be better fleshed out. The user experience is very good, but (for example) the slideshow viewer is broken right now. I don't know about on the iPhone, but on Windows Mobile the site is effectively unusable for me. That's a real shame, as Yelp Mobile is fantastic.
Not including Yelp in the reviews being indexed seems like a pretty big downside. Maybe most of the world doesn't need to read the musings of the yuppie restaurant-philanderer 2.0 crowd, but as one of those myself - I like Yelp reviews. At the same time, it is nice to read what the rest of the world has to say too. In fact, I'm going to try using BooRah instead of Yelp for awhile - when I'm at home on my laptop at least.
Shortcomings aside, combination of semantic indexing and natural language sentiment-processing is a very interesting one. I look forward to BooRah getting better and bringing the same strategy and feature-richness to other niche topics.
Disclosure: I have a consulting relationship with a somewhat related, still-unlaunched, service provider.