Attention agents
I recently came across a km article called Avoiding Information Overload: Knowledge Management on the Internet…it talks about the many aspects of knowledge representation; search engines, ontologies, XML, RDF, metadata, extraction, semantics, etc.
Something I was curious about was its mention of “agents”…one day we won’t need browsers or search engines as your agent will search and retrieve on your behalf based on your “profile”.
The term “profile” could be similar to “attention” in a way…Alex Barnett often explains about the potential of a portable attention file where you can plugin to a service and cut to the chase (the service will seem to know your interests, and personalise to you).
This attention file is based on your searching (eg. Google personalised search), RSS reading (eg. Findory, Rojo), bookmarks, browser recorder, transactions at services like amazon, etc…
The point I’m making is that this scenario so far is us plugging in our attention file into a service (possibly via OPML)…then when we use the service it will return personally relevant stuff based on our attention file.
What about even further where we ask an agent to stand in for us, give it some commands and it will fetch what we need based on our attention file.
I suppose this has nothing new to do with attention files, but maybe how they could be used by an agent…I think attention files could be very usable in the semantic web.
I find agents or bots similar to search feeds…but what you are doing is saying “go find stuff I like”.
At the moment we collect RSS feeds ourselves, maybe in the future a bot can go looking for RSS feeds it knows we will like based on our attention file (something Rojo does, but this is based on the data Rojo has about us…we need our own attention file made up from all the services we use. I bet if I then plugged this into Rojo, the feed recommendations would be much more tuned).
Further to that, maybe it could replace our RSS Readers…based on our attention file, our bot could trawl the net (not sure if you ask it where to visit) and return a list of daily readings…the more expansive our attention file becomes, the more the bot will seem to know your preferences.
View comment reactions![email.png](http://services.nexodyne.com/email/icon/GxbiQvgbwBgCnw%3D%3D/oIp%2BJMQ%3D/R01haWw%3D/0/image.png"){kind=icon}
Hi John,
I’m the Executive Director of AttentionTrust, a nonprofit dedicated to educating people about the existence and value of attention data, and empowering them to make effective use of their own attention data.
I’m also married to a librarian, so I was thrilled to see you posting on this subject. I look forward to hearing more!
Ed Batista
Comment by Ed Batista — June 14, 2006 @ 5:19 am
Hi John,
As you say there are a lot of web services that are trying to solve this problem in their own way, bu I think for something so span across many sites that the tool needs to be on the client-side.
I posted about this on our blog a few days ago actually:
http://www.touchstonegadget.com/blog/2006/06/power-back-in-your-hands.html
Comment by Chris - Touchstone Gadget — June 14, 2006 @ 12:47 pm
We know that recording attention is easy, but what is not easy is to own your own attention - your searching data, RSS reading behaviour, interactions with web services (eg. purchases)…I guess this is browser data, social websites you are a part of, etc…
Sure each service I use can tailor the service to my attention behaviour so it can serve me better eg. touchstone, findory, etc…
But I want to own every movement I make with every service I use…then I can plug this in and give a new service I use a head start (a bit of pre-tuning).
Something has come to my attention (pardon the pun) and that is a post by Paul Montgomery, who says that attention recording may be dangerous if we were to do it ourselves using a non-profit start-up, because of the potential of being bullied with greater effect by big brother, over a big company like Google or Microsoft.
Here’s the post: http://tinfinger.blogspot.com/2006/01/trust-google-or-trust-attentiontrust.html
See more: http://www.techcrunch.com/2005/10/05/attention-trust-recorder
Comment by Johnt — June 15, 2006 @ 2:29 am