From mboxrd@z Thu Jan  1 00:00:00 1970
X-Msuck: nntp://news.gmane.io/gmane.emacs.gnus.general/9061
Path: main.gmane.org!not-for-mail
From: Hans de Graaff <J.J.deGraaff@twi.tudelft.nl>
Newsgroups: gmane.emacs.gnus.general
Subject: Re: adaptive word scoring
Date: 02 Dec 1996 12:46:00 +0100
Sender: graaff@duticai.twi.tudelft.nl
Message-ID: <yahlobh2mpz.fsf@twi.tudelft.nl>
References: <199611290525.VAA00464@kim.teleport.com>
NNTP-Posting-Host: coloc-standby.netfonds.no
Mime-Version: 1.0 (generated by tm-edit 7.94)
Content-Type: text/plain; charset=US-ASCII
X-Trace: main.gmane.org 1035149143 16249 80.91.224.250 (20 Oct 2002 21:25:43 GMT)
X-Complaints-To: usenet@main.gmane.org
NNTP-Posting-Date: Sun, 20 Oct 2002 21:25:43 +0000 (UTC)
Return-Path: <ding-request@ifi.uio.no>
Original-Received: (qmail 25318 invoked from smtpd); 2 Dec 1996 12:07:09 -0000
Original-Received: from ifi.uio.no (0@129.240.64.2)
  by deanna.miranova.com with SMTP; 2 Dec 1996 12:07:08 -0000
Original-Received: from duticai.twi.tudelft.nl (duticai.twi.tudelft.nl [130.161.159.1]) by ifi.uio.no with ESMTP (8.6.11/ifi2.4) 
	id <MAA28321@ifi.uio.no> for <ding@ifi.uio.no> ; Mon, 2 Dec 1996 12:46:14 +0100
Original-Received: from dutifp.twi.tudelft.nl (dutifp [130.161.159.118]) by duticai.twi.tudelft.nl (8.8.3/8.8.3) with ESMTP id MAA07198 for <ding@ifi.uio.no>; Mon, 2 Dec 1996 12:46:05 +0100 (MET)
Original-Received: (from graaff@localhost) by dutifp.twi.tudelft.nl (8.8.3/8.8.3) id MAA20768; Mon, 2 Dec 1996 12:46:02 +0100 (MET)
Original-To: ding@ifi.uio.no
X-Face: ,i^c$X{l+r}VV%(bl{^[<Y3kgt`*)]&phO\8odM1n4R$1@IVjV\3J"vkO)w+s+5_VxCAdXlzTJxo'?)vSka?BQJF04Rx38XdL12h]q/e2~1OXLsVT_re
In-Reply-To: Felix Lee's message of Thu, 28 Nov 1996 21:25:08 -0800
Original-Lines: 23
X-Mailer: Red Gnus v0.72/XEmacs 19.14
Xref: main.gmane.org gmane.emacs.gnus.general:9061
X-Report-Spam: http://spam.gmane.org/gmane.emacs.gnus.general:9061

Felix Lee <flee@teleport.com> writes:

> so after using adaptive word scoring for a while, I've decided that
> it's mostly useless.

One thing that struck me is the defaults for word scoring. They cause
scores to increase of decrease at an incredible rate, making all
scores useless. I've changed the scores to -1 and 1, and this seems to
work much better. I also think that line scoring is more important
than word scoring (i.e. word scoring to extrapolate to subjects which
have not been scored yet), so setting the word scores to some small
number makes much more sense than the current defaults.

> say you're an avid fan of alt.sex.pictures.emacs.  the word "gif" is
> fairly common and mostly neutral: you can't tell if an article is
> interesting based on the word "gif".

Yes, this doesn't work well. I've noted this also in other groups
(e.g. comp.fonts), and have decided that in those cases it's no big
deal, because it means that more descriptive subjects get better
ratings.

Hans