Hot on HuffPost Tech:

See More Stories
Engadget for the iPhone: download the app now
AOL Tech

Twine: A social network built on the semantic web dls interview

There's been a lot of talk over the last few years about the semantic web. While Google and other search engines do a pretty good job of ranking web pages and providing relevant results to keyword searches, the truth is that Google doesn't really understand what you're asking it. Not in plain language anyway. We've learned to tailor our search habits to search engines as much as they've learned to adjust to our preferences.

The concept of a semantic web is based on the idea that machines can be taught to understand language more like the way people understand it. For example, a semantic web search engine would know the difference between John F Kennedy the person and John F Kennedy the airport. But the truth of the matter is that Google does a pretty good job of meeting your search needs. And that's why we were interested in speaking with Nova Spivack, the CEO and Founder of Radar Networks, one of the companies pioneering the Semantic Web.

Today Spivack is announcing Radar's first product. Twine is a "knowledge network," built on a semantic web platform. Basically you can think of Twine as a cross between Facebook and Google, with a little bit of thrown in for good measure.

We asked Spivack why Radar would focus on a social application rather than a search engine, and here was his response:

"Google's mission is to organize the world's information. And our mission is really to organize your information. Your information is really the most important information in the world. It's the other 90% of the information that Google isn't indexing really. I think that Google is doing a wonderful job of crawling the web. And in fact it's something that we plan to leverage. Certainly I don't think that it would make a lot of sense for any company today to directly compete with Google. And in fact, there's lots of opportunity in areas that Google isn't really strong at. And this is one of them."


In a nutshell, Twine is a full-featured web application for organizing your information and sharing it with your friends, family, or the public. You can upload your contacts, pictures, or notes from your desktop. Or you can save content from web sites including text, videos, and images. Twine has a handy bookmarklet for grabbing content and metadata from other websites and importing it.

Once your content is on Twine, the site goes to work analyzing the data and generating tags. It can figure out if keywords refer to people, places, or things. Clicking on a tag will bring up all the information you've saved that's related to that tag, as well as information that other people in your network have shared.

We're not entirely convinced that Twine accomplishes much that you couldn't do with a really cleverly-built social network. But since the site incorporates natural language search features, over time it will become easier and easier to find exactly what you're looking for when you enter a query into Twine's search box. That information will come from data you've collected, and from your trusted sources as well as the general public.

You can listen in on the rest of our conversation with Nova Spivack as he explains what makes Twine tick:

Or you can download the MP3 version and listen on your way to/from work.

Twine launches in private beta on October 29th. If you can't get your hands on an invite, you'll probably have to wait until the spring to check the service out.


Tags: nova-spivack, radar-networks, semantic, semantic-web, twine