Radar Networks, the not-so-secret stealth startup, is finally unveiling its site, dubbed Twine. Twine is targeted straight at groupware and knowledge-management apps that have mostly been confined to enterprise installations, and opening that up to a broader base of consumers. The startup has raised $5 million from Paul Allen, Peter Rip, Ron Conway in April, 2006, and has done work for DARPA.
CEO Nova Spivack took me through a demo. On the surface, Twine is a place to organize information you find or create on the Web—bookmarks, notes, videos, photos,contacts, tasks. (A Web browser plug-in makes it easy to save stuff to your Twine wherever you may find it on the Web). 
You can also share that information with a private group or publicly. Once you ingest in all the information you want to organize, Twine applies a semantic analysis to it that creates tags for each document or video or photo. The tags match up to concepts that Twine’s algorithms associate with each piece of content, regardless of whether that concept is specifically mentioned in the Web page or other content being tagged. For example, you might bookmark this post and Twine would create tags for all the people mentioned in it (Nova Spivack, Paul Allen, Peter Rip, and Ron Conway). It would also create tags for the organizations related to the post, such as Radar Networks and DARPA, but also Paul Allen’s venture firm Vulcan Capital—even if Vulcan was never mentioned in the post.
What Twine does is automatically generate smart tags and connect them together. There is also a social element. If you share a Twine with others, each piece of content that someone brings into that online space is associated with that person. So when you do a search, the results that come back are influenced not just by the tags, but also by who put the information into the Twine in the first place. “It’s the wisdom of crowds plus the wisdom of computers working together,” says Spivack. The more closely related that person is to you, the higher the relevance. At the same time, Twine is creating a very detailed profile of your interests which it hopes to run highly targeted ads against.
Twine is putting structure onto all of this unstructured data that is out there by analyzing it and adding tags to it that are connected together. The network of links between these tags is something that Spivack calls the “semantic graph,” which includes the “social graph” that is made up only of those tags categorized as people. Bu the semantic graph is bigger than that, comprising other tags such as organizations, places, and other categories.
Rather than create a semantic index of the entire Web, which would be a huge undertaking, Spivack is starting with just those parts of the Web people feel are important enough to save in their collections. Then he applies natural language processing and semantic indexing to just that data. “If you just sucked in the whole Web,” he says, “you would get stuff people didn’t want. Here we are looking at who thought it was important and why.” It’s also cheaper to do it this way, since it’s a more limited set of data that needs to be run through Twine’s semantic engine.
Everything in Twine will become widgetizable and exportable elsewhere. There will also be a full set of APIs. All the data will be able to be taken in and out. Other search engines will be able to index anything in a public Twine, along with the smart tags that have been appended to the information there. “When you put stuff into Twine,” says Spivack, “Twine enriches it, but you can take it out.” Of course, all of those enriched tags will point right back to Twine. “We’re the only place that can even see the connections between things,” says Spivack. Well, not quite yet. People have to start using Twine first.
It will be interesting to see if Google, Yahoo or Microsoft attempts this technology as a labs beta
This still doesnt address the problem of our online identity exsisting in differnt silos….
I wonder if they their bet is based on an assumption that sharing information and tools for sharing is going to replace web searching?
I see why this is cool from a provider/producer perspective, and I see why Twine’s tags will make search interesting once everyone uses it, but where is the value for the consumer now? There are already about a million ways to bookmark things, many of which also allow one to search through one’s bookmarks.
Businesses like network effects because, long term, they’re one of the best sustainable competitive advantages out there. But you need to offer enough initial value for people to jump on board. It’s hard to get the mix right, and I’m not sure Twine has.
These kinds of services are extremely useful for highly specific searches. I now use del.icio.us quite frequently over Google for a QUALITY tutorial or software download page.
- myLook
If you are online that much, you don’t have a li…….
Oh never mind!
ttp://fakesteveballmer.blogspot.com
Just a note — Radar Networks has not raised money from DARPA and we are not DARPA funded. We did however subcontract on a DARPA funded SRI program, CALO (”Cognitive Agent that Learns and Organizes”) for a few years, several years ago, in the early stages of research. If you could note that, I would appreciate it.
I like the idea of semantic analysis and tagging features, I hope that will help to let the content travel fast. Thanks for the detail.
Funny, their logo looks pretty similar to TripIt. What’s with all the generic logo graphics lately?
Sounds like a perfect match for AOL junk, why dont they picth this idea to them - AOL might be very interested in it. Why do people re-invent the wheel? There are already gazillion applications that do this, and BTW Google will crush it in no time - pretty soon.
Wow, I read the article, ran over to the twine site and signed up for the beta then read the few comments here and can’t help but wonder… Am I the only consumer that is excited about this?
Nova! Pick me! Pick me!
I’m ready to test this, since it seems quite useful both for my personal junk as well as work stuff.
I tried signing up for the BETA as this looked very useful. My browser (or their site) froze. Then I tried registering again and the message back indicated that my e-mail address already existed. So I figured that I was registered after all. And then ….. I looked for a lost password link (since the system) never prompted me for one prior to freezing the first time. And there was none. So now I am posting here because this site doesn’t freeze and I want these guys to know that their server may be over-subscribed. Like posting on Tech Crunch won’t generate traffic — DUH!
@Phillip - I’m excited too.
This sounds like it has great potential. I almost see it like a del.ic.ious / digg (bookmarking, tagging, social sharing, etc) but add in smart tagging (cause I hate labeling stuff) and then combine that with search results that prioritize by what you and your friends have submitted… friggin’ sounds sweet.
Hope it’s executed well. C’mon beta!!!
@Les - same thing happened to me.
@Nova Spivack - If you read this please let us know if our emails got accepted for beta invites. Thanks.
I just went to the site and found the following:
“Due to enormous popularity, our servers are experiencing extremely high loads.
If you wish to register for Beta, please send an email with your name, email, and organization to info@twine.com.”
Seems like the pressure may have been too much!
Twine appears very interesting idea however it seems NosyJoe does pretty much the same job although taking kinda different approach and seems simpler. Based on the content submitted by the users NosyJoe.com’s engine extracts the meaningful components like sentences, phrases and keywords from the content and makes it meaningfully searchable, web visible and findable, clusters it into contextual channels and smart tags and applies a set of algorithms and user patterns to further ranking, mashing and sharing
http://www.nosyjoe.com/tags/twine
man if the spooks have funded this, i won’t use it for anything, go ahead and put your whole life in their - i’m sure the gov would love to troll the database. hopefully radar isn’t using it for gov-sponsored research
chilling
@John F.
Above and beyond the potential for information sharing between friends, I do an immense amount of searching for stuff at work. Rare and hard to find information gets printed (so I have a hard copy in case the original site goes poof) and bookmarked (del.icio.us). For a while I was using clipmarks (to avoid having to hard copy stuff), and so on and so forth.
I’ve considered setting up a wiki for paraphrasing and reference links. The problem with this is that I don’t have the time at work to always make these notes for the wiki, etc. Having something that bookmarks, allows notes, tasks, etc. sounds like a godsend.
Yeah, there’s stuff out there that does this (mostly diverse services for different aspects), but the icing is the semantic bit and the auto-tagging. If twine begins even half as great as this sounds on paper, I’ll be a happy camper.
@john
Read comment #7 by Nova regarding the DARPA bit.
@NosyJoe
Interesting… But I don’t think these are comparable. Obviously I don’t have hands-on experience with either Twine or NosyJoe, but from what I’ve gathered NosyJoe relies on user submissions for interesting stuff then runs it through the “auto-magic process” (my words, not theirs) for searches. My understanding of Twine is less Digg-like and more on a personal level with the ability to make my collection of stuff private/friends/public viewable (and thus, searchable).
This seems like a different flavor of Freebase.com from Danny Hillis’ Metaweb? Nova, could you illustrate the differences, if any? My first instinct is that this is just a rehashed Freebase - which BTW does not seem to have a great uptake.
Is it just del.icio.us with nice GUI? Looks like it’s a bit more SN like Facebook, it better not go down the Social Network route of Facebook. It’d be great to replace my annoying StumbleUpon and have better intelligence as it claims.