What’s on the menu for semantic technology this week? Two vendors in the foodie field are offering up some new treats.

From Nara, whose neural networking technology is behind a service to help users better personalize and curate their restaurant dining experiences (see how in our story here), comes a new feature that should make picking a restaurant for a group dinner an easier affair. It combines users’ “digital DNA” – the sum of what it learns of what each one likes and doesn’t like regarding dining venues – to serve up restaurant choices that should appeal to the entire group across its range of preferences.

“It’s a really fun way to start getting [the service] into social,” says Nara founder and CEO Tom Copeman.

Read more

Edamam, a semantic company on a mission to help people eat better, recently announced “it will be powering the nutritional information for all the recipes on TheDailyMeal.com, the fastest-growing culinary site of all time. Edamam will use its advanced semantic technology to analyze and provide a full nutritional profile, as well as health and diet labels for each recipe to The Daily Meal readers. ‘As one of the premium online destinations for quality information surrounding all things food and drink, The Daily Meal needed a way to organize and incorporate nutritional labeling for an ever growing database of recipes,’ said Victor Penev of Edamam. ‘Our semantic technology helped solve the problem’.” Read more

Edamam, which has built a food ontology for its food knowledge site (which The Semantic Web Blog initially covered here), is adding an iPad version of its app to its existing iPhone and Android versions. The company also did a full relaunch of its web site to optimize the experience for desktop users, as well, with improved browsing and search.

Originally, the web site app mirrored the mobile versions. But, says co-founder and CEO Victor Penev, “We realized that people wanted to be able to access recipes and search on the desktop, and they should have a holistic experience from anywhere.” While the company had been more focused on the mobile arena, Penev says building traffic for the website is going to be a priority too. Among the capabilities users should see in the near future are functions like one that will let people save recipes on their iPhone or Android mobile devices and then access them on their iPads or desktops, or vice verse.

Read more

It’s time to get semantic with your Thanksgiving meal – or what’s left of it. To that end, we toured some semantically-powered foodie services to get some ideas about what to serve up for the big day. Maybe you’ll even find some things you just may never have considered without some semantic web services making it easy to pinpoint to your tastes (literally) or nutritional concerns, or that let you bring to the table the latest delicacies getting high-fives on the social web sentiment scene.

Here we go:

• Google. For some Thanksgiving-ers, it’s simply off “to the Google,” as the dear family member in charge of our celebration says, to suss out recipes that have been marked up with rich snippets or schema.org microdata. Tired of the same old green bean casserole and plain mashed potatoes each year? Narrow the search engine to its recipes focus and you’ll find a few choice nuggets of Thanksgiving’s best vegetable side dishes – the traditional ones are there, like Martha Stewart’s garlic mashed potatoes (for a bit of a twist) and, yup, the tried-and-true green bean casserole. But you’re not likely to have thought of a pickled root vegetable salad before, courtesy of Cooking Channel TV, are you? Be prepared to set aside an hour and thirty minutes, though, to make it happen.   Read more

Edamam wants to be the one place where all the food knowledge of the world is organized. That’s the goal of co-founder and CEO Victor Penev, who launched the site in April, and recently updated the several hundred major recipe sites in its knowledge base to also include some smaller blog sites that add additional variety.

Semantic technology is helping the company reach its goal. “A big problem is that data about food is very messy,” says Penev. “It’s hard to find something, what you find often contradicts other information of what is good for you and what the calories are. So we set out to solve that problem. We played around with different approaches but settled on using semantic technology.”

The confusion arises in part from the fact that recipe sites themselves usually just hire services to calculate nutritional data. But that may lead to mistakes when calculations aren’t undertaken with exactitude — substituting white cream for heavy cream nutritional details changes the whole profile of the recipe, he says.

So, what is that right semantic stuff? One piece of it is that, in conjunction with Ontotext, Edamam built a food ontology. An ontology can be the foundation for a lot of things, such as extracting the knowledge of the chemical composition of a particular recipe and thus inferring its flavor and texture. And Edamam means to grow its own to include various datasets such as chemical data (for flavor and texture), geolocation (for local and seasonal recipes), product data (for e-commerce). and more.

But initially, it’s taken the simple approach, with the core of the ontology focused around classifying ingredients, nutrients and food. “We have started with the simplest ontology and focused on the most common use case — mobile recipe search,” he says.

Read more