Thursday, November 17, 2005
Taxonomy and Folksonomy

Ramesh Jain writes:


It is clear that the problem of automatically extracting content from images or any other media is a difficult problem. Even in text we could not do it. That resulted in all our search engines using simple keyword based approaches or developing approaches that will have significant manual component and will address only specific areas. Another interesting finding was that for an amorphous and large collection of information, taxonomy based approach was too rigid for navigation. Since it was found relatively easier to develop inverted file structures to search for keywords in large collections, people found the idea of tags attractive. By somehow assigning tags, we could organize relatively unstructured files and search. About the same time that this was found, the idea of the wisdom of crowd became popular. So it is easy to argue that tags could be assigned by people and will result in ‘wise tags’ (because they are assigned by the crowd) and will be much better approach than the dictatorial taxonomy.
...
If everybody assigned several appropriate tags to a photo that she uploaded and then the crowd seeing that photo also assigned appropriate tags then the wisdom of crowd may come in action. But if the up loader rarely assigns tags and viewers, if any, assign tags even more rarely, then there is no crowd and there is no wisdom. Interesting game like approaches (See WWW.ESPGAME.ORG) are being developed to assign tags to images.
...
Based on what I have seen so far, it appears that the success may come from some interesting combination of taxonomy and folksonomy.

Software | PermaLink

Comments

Hi,
I am shopping around to get involved in emerging technologies -and start-ups.I'm 17. Do you have any thoughts on what I can do as a volunteer/intern?
thanks.
ambreen
ambreen@Unt.edu

Posted by: Ambreen on November 18, 2005 12:37 AM

I believe what you are referring to, is also known by the other name "Peer Production" and forms the basis for projects such as Wikipedia and Del.ici.ous. There was a lot of useful insight into this issue in one of the discussions that a New York based VC firm named UnionSquare Ventures hosted with some of the prominent leads in the Web 2.0 environment. They have the transcript of the whole session on the web. You might find that interesting in connection to this topic.

Vijay

PS: Amazon's new revenue-service called HIT (Human Intelligence Task) would also be an extension of this very same ideology.

Posted by: Vijay on November 18, 2005 02:01 AM

We have created a hybrid classification system using both taxonomy and user-defined folksonomy on our new service BroadbandSports.com

The service is the first, video-only sports portal and allows viewers to watch professional and user-generated sports videos and empowers them with ways to “tag”, search, find, store and replay their favorite videos.

The service addresses the problem of finding and adequately “describing’ video by allowing producers AND viewers to “tag” the videos.

As you noted, tagging addresses the technical problem of finding and describing the meaning of unstructured data like video. As more video is available online, the traditional search engines often fail to identify what the video “is about”. “Third-party” tagging addresses this problem by allowing users to define a video’s content and meaning through tags.

This approach solves the inability for the Google and Yahoo’s of the world to accurately describe the contents of video. Search engines do a great job with text and a lousy job with video.


Posted by: Greg Prosl on November 20, 2005 11:32 AM
Post a comment
Name:


Email Address:


URL:


Comments:


Remember info?





Main - Feedback
© Rajesh Jain