Every day I read a lot of news, articles and other information online. Most of it I read through a news aggregator (have tried a few, currently evaluating NewzCrawler), but I also visit a few websites regularly (that don’t have RSS feeds) and people send me interesting links via Instant Messaging or email.
The tips I receive from friends and Wetware readers and the links I find on my favorite blog sites tend to be the most interesting material. The reason is simple. These are hand picked links from people that share (or know) my interests. If I receive a link from a friend via IM, I will always read it. I know they wouldn’t “interrupt me” unless it was something that they knew I would find interesting.
With the sea of information out there, we will increasingly need better mechanisms to make sure that the interesting content “floats” to the surface and using some sort of collaborative filtering seems like a good approach. Obviously several such solutions have been attempted, but none of them has really done the job. Here’s my suggestion:
Some of the more interesting tests to use collaborative filtering to find hot, interesting or relevant content online come – not surprisingly – from the blogging world.
One of them is our much beloved Google. Not surprising that they bought Blogger earlier this year. They’re tapping into the collective minds of hundreds of thousands of web surfers that are continuously surfing the Web to find interesting content and blog about it. Sure enough the content bloggers link to ranges from hardcore porn to speculations on which alien-race that made the latest crop circles, but this is a strength, not a weakness.
In the blogging world you will find people with interest in just about any imaginable topic and by wisely evaluating the relevance of each link, the collective minds of bloggers might well be the best possible source for relevant, quality content on the topics in question.
The biggest problem of this approach might be reinforcing loops, where bloggers use Google to find content to link to and then pick one of the top hits, in turn increasing the rating of the page in question and making it more likely that the next person will do the same.
The other thing I mentioned is blogdex. The service, a research project at MIT’s Media Lab, skims through thousands of blogs in search for links in the most recent entries. It then lists the most linked to articles, thereby “sucking” the zeitgeist from the online community. It gives a really interesting picture of what’s happening online.
Both of these examples are fascinating and work quite well. However, bloggers are only a small portion of the online community and making a blog entry takes a little effort and time.
I want a system – the Interesting Content Indicator – where I can simply press a button to say “This is interesting!” (perhaps also giving a rating). My indication will be noted by the system and as I submit more and more URLs (I guess I would myself submit something like 5 a day), the URLs I’ve posted will be matched to URLs other users have posted to match users with similar interests. In return I will get my personal RSS-feed with URLs that other users with similar interests have indicated as interesting.
The beauty of the ICI is the simplicity. All the user has to do is clicking the “Interesting” button whenever he or she finds something interesting (could e.g. be implemented in a similar way as the “Blog this!” or “MT it!” buttons of Blogger and Moveable Type), and in return the user will get an extremely valuable service.
There are some additions that might improve the service. One could be keyword matching that would not only create my profile based on the URLs I’ve submitted but also based on keywords from the articles I’ve indicated I find interesting. Another one might be to allow some categorization of the indicated URLs. Alerts when a topic becomes “smoking hot” might also be an idea.
I’m still not entirely sure that these would be improvements. “Keep it simple” applies as never before.