Bayesian Aggregator
Posted on:: December 2nd, 2003
In a comment, Kevin Jordan writes:
348North News is a normal aggregator in much of the way you think of it. However, it allows me to identify keywords or themes that it puts together into phrases — and then matches up the phrases with like articles. Like a cross between Google News and Daypop (but that makes it sound much more complex than it is).
If you want to see an “interests” based summary for me, check out the Phrase Index. I use fairly general keywords so as not to miss out on the future items.
I haven’t tried it, but the approach sounds promising.
Categories: Uncategorized dw
Where’s the “Bayes?” Is this aggregator using a statistical analysis approach to flagging feeds of interest, or is it just matching phrases to text found in the feeds? An aggregator that can analyze the source and let me flag “More like this” or “Not interested” could really help focus the flood of feeds and prioritize the important from the trivial. How are you implementing this? And where’s the source? Care to share it?