BooRah - Inside the Buzz

We’re staging a new look for BooRah here. Over the past few months, we’ve received a lot of feedback and we’ve tried iterate on some of it. The biggest area of focus was to reduce the clutter of links and text and organize the page flow a bit better.

Do the web pages look better now?  Did we reduce some of the link and text clutter from our current version of restaurant search website here.

You’ll also notice a new feature on our city profile pages and restaurant detail pages to showcase some of our semantic meta data. Each restaurant detail page now features “Top Sentiments” from all the reviewers across all the sources we’ve aggregated and you can instantly get a gist of what’s popular at that restaurant. The city profile page now shows, “best-of” categories for you to explore various dining options. E.g Mountain View city page offers recommendations such as “Best Weekend Lunch ” at Cafe Baklava, “Best parties” at Xanh Restaurant and “Best Lunch Buffet” at Amber India.

Take our new website for a spin and let us know what you think.  Please leave feedback in the comments section here.

Last week was the annual gathering of search engines and folks from search industry at SES in San Jose. It is amazing to see how mature the search industry has become by seeing 1000’s of people show up even in a down economy. Many of the key industry thought leaders including Google, Yahoo, Microsoft and others were present to share their ideas and thoughts.

Here are  my top 3 takeaways from the conference:

1. Search enhancements continue to focus around relevance and engagement. Relevance is highly dependent on user intent and search engines are spending a lot of time analyzing ways of getting to user intent. I was on a semantic search panel and we had a very thoughtful discussion around the future of open search and how semantic search could increase relevance for consumers. Here’s some very good coverage about the session by San Francisco Chronicle, InternetNews.com and ClickZ about the session.
2. Long tail is becoming highly relevant and more companies are beginning to capitalize from search and advertising perspective. There were a couple of sessions that discussed how advertising on the long tail networks such as looksmart or quigo could be significantly advantageous compared to the larger networks ( although the volumes still aren’t available). Consumers are also beginning to explore the power of search engines by trying long tail queries specifically for products and local services. Infact we here at BooRah are also seeing a decent increase in long tail volume for restaurants.
3. Though mobile wasn’t a big topic nor was local search, many of the keynotes and other panels discussed how small businesses were still behind the 8-ball and how newer phone platforms such as IPhone were really driving adoption ( not just in the major metro areas but also middle America). Kelsey group hosted a couple sessions around these themes and were very informational.

I could only attend the first day and a few other sessions of interest, but all in all, the conference was very well organized with some good keynotes and networking opportunities. Thanks to staff of SES for a great conference!

Yahoo, this morning announced the winners of it’s SearchMonkey contest. And, we are glad to have won the first prize in the InfoBar category. Special congratulations go out to our team member, Shrisha Radhakrishna, who spearheaded the integration effort.

SearchMonkey is the first of many initiatives for Yahoo’s Open Strategy (See ReadWriteWeb story). Earlier this week, Yahoo also announced a program to open up their existing API’s for unlimited use with no restrictions on branding/linking. We’re excited to make use of Yahoo’s open platform, with our semantic technology, to enhance the user experience and relevance for our customers. Kudos to Yahoo for taking such a bold step in the tumultuous world of Search.

Now for the details of our InfoBar implementation:

InfoBar is an application within SearchMonkey that allows additional information to be shown along with the search result. Below is a search result for “best restaurants in san jose” that has been enhanced by InfoBar (NOTE: You’ll need to be logged in to Yahoo and add the BooRah application in your profile to see these results. See post for instructions).

By expanding the search result, you can see the enhanced result within the same page.

You’ll see the top 3 restaurants and their overall ratings along with a link to start exploring the site, providing a preview of what to expect when a user lands on the site. For this result example, “Falafel drive Inn” received a 93% positive rating based on 353 reviews, “Maggiano’s” scored 89% out of 324 reviews and “Original Joe’s” scored 82% based on 290 reviews. This information was all derived from the sentiment in the written text of the reviews using BooRah’s patent-pending NLP engine.

Here’s another example — a search for “oola in san francisco“. The specific restaurant search is enhanced by displaying the most relevant attribute “tags” that were extracted from the user reviews:

In this example, “oysters”, “chicken ravioli”, “bartenders”, “fish dishes”, etc., were highly raved about in the user reviews. We also provide drilldown on ratings for food, service and ambiance to aid user evaluation before leaving the search results page.

We hope you’ll add BooRah InfoBar application to your profile and enhance your search results and relevance next time you search on Yahoo!

Yahoo’s SearchMonkey is a unique step in opening up search to publishers to enhance the quality of the search experience for consumers. Earlier this week, Alex Iskold over at ReadWriteWeb wrote an interesting post quoting Peter Mika about how meta data needs to be on the page for users to see and experience it. We, at BooRah, have focused not only on extracting structured meta data such as tags, ratings etc., but also inferring relevant meta data from sentiments in user reviews (in restaurants for now) using sentiment extraction technology. The following listing is an example of search result on Yahoo for a popular San Francisco restaurant - Oola.

This first page listing for Oola in San Francisco contains more relevant information for a consumer than any of the other search results on that page. With one click, one can see the restaurant’s menu, make a reservation, write a review, and get discounts!. Also, based on our inferred meta data, the user sees that “ahi tuna appetizers”, “oysters” etc.. are worth exploring at that place. Furthermore, the granularity of the rating helps users that are looking to dine out on special occasions.

To see our enhanced results in Yahoo for your searches,  visit http://gallery.search.yahoo.com/application?smid=wKB and select the “Add Infobar” button .

So, take BooRah’s SearchMonkey implementation for a spin and let us know what you think.

Here are two search queries that I’ve been pointed to, that deliver great relevance on BooRah.

• Restaurants with Great View in San Francisco
• Restaurants that serve Idly Sambar near 110 Rio Robles, San Jose

For the “great view in San Francisco” search, the results were really good, but what amazed me was the accompanying map that lends credibility to the results.

The second search is something that I’d do often but have not tried it until now. Idli Sambar is a south indian breakfast, snack, appetizer item that is a very frequently ordered at a south Indian restaurant. Not only are the results on the attached screen right on, but if you search for other options beyond the 5 mile radius( idli sambar beyond san jose), you get the complete list of places for you to choose from, which is perfect (atleast for Shrisha and my tastes).

What are your favorite searches on BooRah?

In the past few weeks we have gotten a lot of concrete feedback on areas for improvement/features on our website. We have deployed a new release with the following major features/enhancements:

a) Mobile Support: You can now search our entire database of restaurants on your phone using a very simple and easy to use interface. For most of the phones, if you select http://www.boorah.com, you’ll be automatically redirected to the mobile site. Where we cannot detect the user-agent for your phone, please enter our mobile restaurant search website (http://www.boorah.com/restaurants/m). The search results are exactly the same as you’d get on the Web and you’ll also see a simple summary of the restaurant in addition to our ratings for the restaurant. Mobile is where sentiment extraction and summarization are extremely valuable and this is our first release.

Here are a few examples of queries that may be highly relevant on phone:

Pizza in Mission, San Francisco

sushi in 94123

indian at El Camino and Castro, Mountain View

The search results are sorted similar to what you’d get on the web at boorah.com. The following screen shots are simple 2 level drill down to get the details and additional information.The summary and ratings are generated by our patent-pending summary and scoring system.

The following details screen shows number of reviews, overall popularity (expressed as %Rah) and a system generated summary.

PS: We’re adding support for maps and directions soon.

b)Navigational Enhancements between City and Metro Landing Pages - We have made our navigation between metro and city pages simpler( atleast we think so). The metro pages primarily provide navigational help in selecting a city. Also, if someone wishes to search across an entire area ( one might consider doing that for special dining occasions), we still support the “best of searches” across the entire metro area.

We’ve also incorporated a simple map to aid in selecting our coverage or drill down to cities that may not necessarily be listed at the top. We were able to find a very flexible, configurable and versatile map from backspace.com.

c) Search and Other Minor Enhancements - We’ve now incorporated a new full-text search engine in the backend which gives us a big boost on the performance and scalability. We are also making other tweaks to ranking algorithms to improve the overall relevance and search quality. We have also optimized content and spacing on pages.

Check out our new features and let us know your feedback.

 Today announced launch of our service in 6 additional metropolitan areas. This brings our total metro count to 20. Since we started our geographical expansion in late Jan 2008, we have been adding a new metro area almost at the rate of 1/week. Here’s quick links to the top cities in the new metros: Restaurants in Detroit, Orlando Restaurants, Houston Restaurants, Austin Restaurants, Dallas Restaurants, and San Antonio Restaurants

We also announced a nationwide partnership with AmericanTowns.com, a network of community-based websites. Using our Javascript syndication platform, we are now powering restaurants search for 1000’s of cities on their website. E.g  Here’s a link on their website to san francisco restaurants

We are excited at the pace we are able to open up new markets and provide coverage at a national level in a short period.

Monday (04/21/2008) is Alternative Search Engines Day in San Francisco. Charles Knight and the good folks at ReadWriteWeb were kind enough to invite us to participate and share our perspective on NLP search. The sponsoring search engines for this invitation-only event are SeeqPod, UpTake, Matchpoint, HealthPricer, and GoPubMed.

See you there.

Last month, We announced the list of top restaurant bloggers which is compiled automatically by our semantic crawling platform. Simply put, it associates blog posts from various bloggers to specific restaurants and ranks the contributing bloggers. We are seeing great interest in our technology since launch and have gotten some very good feedback. Today, we are launching a feature that enables the contributing bloggers to claim their blog profile pages on BooRah and show case the ranking. Here are a couple of examples:

• Anna Haight of mtkilimonjaro.blogspot.com
• Jo Boston of jobostonisafoodie.blogspot.com

As we gather new blog posts and content from other bloggers, these rankings will dynamically change to reflect the latest ranking. We hope you will find this feature interesting and valuable to showcase your BooRah generated rankings. The process to claim your blogs is very simple. We’ll give you a piece of code that you can drop into your blog. To get started here’s a link to the list of all the top restaurant blogs. You can click on your blog and start the claim process. Here is the top 10 list currently, and you can use the link from here as a shortcut:

1. mtkilimonjaro.blogspot.com - Anna Haight
2. ocmexfood.blogspot.com - ChristianZ
3. pleasurepalate.blogspot.com - pleasurepalate
4. foodandthings.blogspot.com - Food and Things
5. foodhoe.wordpress.com - foodhoe
6. kikimaraschino.blogspot.com - Kiki Maraschino
7. what2order.blogspot.com - kewlio
8. bestburgersfbay.blogspot.com - Scott Kline
9. jobostonisafoodie.blogspot.com - Jo
10. foodieuniverse.blogspot.com - Foodie Universe

At this time, we do not have a easy search tool for other bloggers not listed in this list, but if you will leave a quick comment, we’ll get back to you with your rank and a link to claim your blog.

If you have other thoughts or comments, don’t hesitate to drop a note here.

Last week was a big week for us. We announced the expansion of our restaurant reviews and rating service to 5 additional metro areas. With this announcement, we have now launched over 3000 cities and 225,000 restaurants in 15 metropolitan areas. Since we started our expansion plans early this year, we’ve been able to expand quickly, thanks to our maturing platform. So here’s our current progress - by the numbers:

• Since Late January, we launched 12 new metro areas, which is approximately 1 new metropolitan area/week
• Our restaurant service is now available across 3,000 cities in 16 different states.
• We have added about 500,000 reviews this year bring our total review count to 1,110,000+ reviews.
• In the San Francisco Bay Area, our first metro, we have reviews for 13,500 restaurants (65-70% of all restaurants in the metro area)
• Our review sources not only include popular review sites but also long tail content from bloggers and other influencers. Infact, we analyze over 100,000 blogs and extract reviews and posts dedicated to restaurants. The process of analyzing 1000’s of blog entries every day is completely automated and a result of our patent-pending semantic entity extraction system. See “Top Rated Restaurant Blogs” for more information.
• Our crawler extracts related attributes such as tags, cuisines, pictures, etc., We’ve also integrated with a few strategic partners to offer menus, reservations, takeouts and discounts. To date, we feature -
  • 45,000 Restaurant Menus
  • 35,000 Pictures for Restaurants
  • 4,000 Restaurants with Online Reservations
  • 8,500 Restaurant Discount Coupons and Offers
• Our NLP engine extracts “Boos” and “Rahs” from user reviews and has identified over 10 Million sentiments from the reviews todate. This meta data powers our summaries and ratings which you see on the website.