Traumwind - why bayesian filtering won't cut it in aggregators

I think the bayesian filter approach (as in email/spam) has one major drawback/shortcoming when used for aggregators:
I'm not only interested in one kind of post/topic, but rather a few categories, that can be varied and very different. And also I might on accident find something totally new, which I'd in the future also like to read... A bayesian filter can't help here.

What is needed is a way of 'more like this'... A way to mark posts I like and have the aggregator show me otheres that are similar...

And a list of categories with a 'sample corpus' for each will not really help... categories are to unflexible and not ad-hoc enough to be really easy to use (need thinking about). Similar entries like I have here are a no-brainer user-wise. Just find a post you like and browse fron there...

read this post form some very cool ideas... (using the most intersting tokens to query feedster for other feeds)

[ by Martin>] [permalink] [similar entries]

similar entries (vs):

I don't know (# 12%)
Working with Bayesian Categorizers (# 11%)
freshmeat.net: Project details for Bayesian Pattern Filtering Library (# 10%)
my own RSS-reader (# 10%)

similar entries (cg):

I don't know (# 4%)
ok, it's proven (# 4%)
good idea! (# 4%)
some more Bayesian Perl (# 4%)
Filters... (# 3%)
freshmeat.net: Project details for Bayesian Pattern Filtering Library (# 3%)
now what again? (# 3%)

relevant words

Martin Spernau
© 1994-2003

Big things to come (TM) 30th Dez 2002

Intentions -nobility of -humility of -credibility of
Oblique Strategies, Ed.3 Brian Eno and Peter Schmidt

amazon.de Wunschliste

usefull links:
Google Graph browser
Traumwind 6-Colormatch
UAV News

categories (1.6)
bayesian (1.4)
aggregators (1.4)
post (1.1)
filter (1.1)
help (1)
like (1)
similar (0.9)
accident (0.9)
otheres (0.9)
www.jimohalloran.com (0.9)
unflexible (0.9)
ad (0.9)
http://www.jimohalloran.com/archives/000230.html (0.9)
fron (0.8)
varied (0.8)
find (0.8)
read (0.8)
corpus (0.8)
drawback (0.8)
tokens (0.8)
totally (0.8)
cut (0.7)
are (0.7)
sample (0.7)
browse (0.7)
feeds (0.7)
feedster (0.7)
way (0.7)
really (0.7)
interested (0.7)
also (0.7)
not (0.7)
a (0.7)
intersting (0.7)
aggregator (0.7)
here (0.7)
i (0.7)
filtering (0.7)
major (0.7)
query (0.7)
very (0.7)
future (0.6)
email (0.6)
posts (0.6)
and (0.6)
approach (0.6)
ideas (0.6)
entries (0.6)
to (0.6)
form (0.6)
mark (0.6)
enough (0.6)
needed (0.6)
thinking (0.6)
in (0.6)
won (0.6)
few (0.6)
different (0.6)
one (0.5)
show (0.5)
user (0.5)
have (0.5)
easy (0.5)
can (0.5)
list (0.5)
each (0.5)
for (0.5)
be (0.5)
used (0.5)
of (0.5)
the (0.5)
cool (0.5)
kind (0.5)
rather (0.5)
most (0.5)
this (0.5)
something (0.4)
why (0.4)
using (0.4)
other (0.4)
that (0.4)
need (0.4)
might (0.4)
think (0.4)
when (0.4)
which (0.4)
no (0.4)
new (0.4)
is (0.4)
use (0.4)
has (0.4)
will (0.4)
there (0.4)
only (0.4)
more (0.3)
just (0.3)
what (0.3)
about (0.3)
me (0.3)
some (0.3)
as (0.3)
but (0.3)
you (0.3)
with (0.3)
on (0.3)
it (0.2)
martin (0.1)
(0)