Universally Tagged Folksonomies
Danny Ayers posted a recent note about “Using those profiles“, indicating his interest in combining his profiles with various applications so they could collectively provide more actionable data points.
This data is already being created and published, it just needs integrating and usefully exposed for browsing/search/navigation. Aggregation of feeds is straightforward, but in general lacks the deep integration needed to get the full benefit.
In this same post, he mentions the “Add-A-Tag algorithm” developed at the Women’s Postgraduate College for Internet Technologies (WIT). It’s billed as a method for learning adaptive user profiles from tagging data (demonstrated with data from del.icio.us).
Due to the high popularity of folksonomies, a large amount of metadata is available. This collaboratively created data is a valuable resource. If a user’s tagging data is treated as a continuous stream of information about a user’s interests, it can be used to create a rich user profile. The profile should represent the most important parts of a users‘ behaviour. Both persistent long-term interests and transient short-term interests should co-exist in the profile.
This approach proves out a number of things that I think we all intuitively understand. Further, it provides a useful foundation to discuss their implications. The question now is what applications can be brought to market such that the research can be converted to utilities for those of us swimming in a sea of content?
To that end, at matchmine we’re cooking up what we believe to be a kewl solution. To help us get there, we’re looking for smart folks driven to see statements like these a reality. We’ll be adding official job postings soon, but in the meantime drop me a line if you’d like to toss your hat in the ring.
