Subject:
|
Re: Article scoring
|
Newsgroups:
|
lugnet.admin.general
|
Date:
|
Mon, 6 Mar 2000 04:38:16 GMT
|
Viewed:
|
901 times
|
| |
|
|
In lugnet.admin.general, Todd Lehman writes:
[snip a lot of math]
> sum(V,1,n)
> = ------------ , V[1..n] defined, with V[1]=0
> n
>
> What amuses me most about this is that the 1 - 1/(n+1) softener can actually
> exist as *part of* the classic pure-linear averaging function just by a very
> slight and trivial alteration of the way votes are accumulated.
where in here does it take into account how many people are in the group? Can
you weigh in the number of people who are subscribed to that group? Since they
are the ones most likely to vote/notice posts to it... ?
Also, (Jenn asks, and I forget if you mentioned this before), will it be
possible to vote through the news/mail interface?
:)
Dan
|
|
Message has 1 Reply:
 | | Re: Article scoring
|
| (...) Implicitly in the n variable; nowhere explicitly. (...) Well, it's nearly impossible to know the number of people subscribed to a given group, and it's even more impossible to know how many people have read and understood a given message. It (...) (25 years ago, 6-Mar-00, to lugnet.admin.general)
|
Message is in Reply To:
| | Re: Article scoring
|
| Upon more reflection, I'm thinking that the "square-rooted-average" sum(V,1,n) w = ---...--- sqrt(n) isn't so great afterall. Its biggest plus is that it distinguishes nicely between sets of votes which have the same average and a different number (...) (25 years ago, 6-Mar-00, to lugnet.admin.general)
|
52 Messages in This Thread:
 
 
- Entire Thread on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
This Message and its Replies on One Page:
- Nested:
All | Brief | Compact | Dots
Linear:
All | Brief | Compact
|
|
|
|
