When I worked at BA we had an appalling pay award system. Everyone was given a rating between 1 and 5, then your salary increase was calculated automatically on the rating. Here’s the appalling bit. You had to apply a normal distribution to the ratings within a group, however good or bad that group was compared to other parts of the empire.
So my boss and I, who didn’t like inflexible systems, used to work the system to make sure that we got the results we wanted, rather than the results the system automatically generated.
Here on Nature Network blogs we have a similarly arcane system that rates how popular a blog is, using some combination of factors, but obviously linked to number of comments.
So this post is an experiment in working the system. Specifically it is investigating two hypotheses:
- That it doesn’t care who does the commenting including the writer of the blog
- It is highly dependent on the number of comments.
So lets see…
What
I
want
to
do
is
see
if
a
lot
of
self-
contributed
comments
shift
the
ranking.
If
they
don’t
I’ll
have
to
ask
the
rest
of
you
to
add
lots
of
comments.
So
far
no
change.
Of course, the powers-that-be could spoil the experiment by deleting this post or even revealing the algorithm for calculating blog popularity – but that would spoil the fun.
So
I
need
more
comments
from
the
rest
of
you
to help subvert the system!
Apologies, I’ve probably filled the snapshots of anyone who watches this blog. That’s experimental science for you – never considering all the side-effects.
Bzzz. Deviation. That last comment had more than one word.
Very quick on the buzzer there Bob. Well spotted.
Brian, you’ve certainly clegged up my snapshot screen – sigh.
Excuse me, madam, but does this bus go to the station?
New Metrics for Blog Mining
ABSTRACT
Blogs represent an important new arena for knowledge discovery in open source intelligence gathering. Bloggers are a vast network of human (and sometimes non-human)information sources monitoring important local and global events,
and other blogs, for items of interest upon which they comment. Increasingly, issues erupt from the blog world and into the real world. In order to monitor blogging about important events,
we must develop models and metrics that represent
blogs correctly. The structure of blogs requires new techniques for evaluating such metrics as the relevance, specificity,credibility and timeliness
of blog entries. Techniques that have been developed for standard information retrieval
purposes (e.g. Google’s PageRank) are suboptimal when applied to blogs because of their high degree of exophoricity,quotation, brevity, and rapidity of update. In this paper, we offer new metrics related for blog entry relevance,
specificity, timeliness and credibility that we are implementing in a blog search and analysis tool for international blogs. This tools utilizes new blog-specific metrics and techniques for
extracting the necessary information from blog entries automatically, using some shallow natural language processing techniques supported by background knowledge captured in domain-specific ontologies.
Brian Ulicny, Ken Baclawski, Amy Magnus
VIStology, Inc., 5 Mountainview Dr., Framingham, MA 01701
Air Force Office of Scientific Research, 875 North Randolph Street, Suite 325 , Arlington, VA
22203
You’ve changed from a face-off to a beard, Graham. Did I miss something?
Metrics for blogs would be something else to have a stimulating discussion about, indeed. Maybe I’ll do a bit of cross-posting.
Brian, how much time do you have on your hands on a Sunday? ;-)
New metrics? I’ve only just got used to metres and grammes.
@ Bob – Nice line by one of my Swedish chums last time the crew came to Scotland 3 years ago:-
“Is it true that in the UK you are going Metric – inch by inch?”
@ Maine – As to the change of my profile pic, simply fancied a wee change.
test
Bob – rats. I was trying to do a Clement Freud, but I came over all Paul Merton.
Maxine – How much time do I have? Come on, it was a wet Sunday afternoon in Wiltshire! All the time in the world. (Ooh, arrr.)
If I sat there long enough tofile fifty comments on my own blog on a Sunday, irrespective of the weather, I’d be divorced. As it is we went to see Prince Crapsian.
I’m
not
sure
this
is
helping
you.
Oh, you’re number two on most commented on.
Graham, I now realise it isn’t a beard, but rather it is some strange kind of head gear. Any back-story to that?
Right then.
Joint first now?
Yay! So let’s put Brian fully into the lead.
(sorry, Jenny)
@ Maxine,
Here is a easier to view version:-
Any back-story to that?
Yes, but i’m afraid I can’t divulge.
Need any more comments?
The more the merrier.
If Firefox could get into the Guiness Book of Records for having the most downloads on a single day (which it inevitably did because no one had tried before) how about a record attempt for most comments on a single post?
exactly
which
record
what
is
the
current
record)
are
we
trying
to
beat.
This is seriously going to mess up the Network Snapshots of all of our contacts. But, The number of comments I made is simply a reflection of how firmly I support your point.
I
think
you
will
-wind-
find
that
the
-compact disc-
record
currently
stands
at a
whopping and sensational
149 as set recently by Rohn et al.
Goodness gracious me!!! Welcome to the Century club Mr Clegg. How did you do it? We’ll never evah know.
Oh dear, oh dear.
Anyone for a game of Cheddar Gorge?
As in this Century breaker by a certain BO’H? At a fertile 110 comments, is there
goldstill some lead in this gorge? Go check it out.—
Now then, now then, ow’s about, jingle jangle this “Record Breaker” attempt of 400 in under a minute !!
Does this bus go the drum shop? – featuring Cozy Powell and Roy Castle
For anyone reading this particular comment unaware of “Record Breakers” – here’s the wiki.
Ah, Roy Castle. Very nice man, shame about the acting in the Dr Who movie. (Anyone remember the Dr Who movies with Peter Cushing in the lead? I quite liked them when I was 11 (quite fancied the circa 11-year-old granddaughter) – for no obvious reason, they mucked around with the whole mythos, and made the Doctor just a wacky human inventor. (As I recall, the other Cushing Dr movie had Bernard Cribbins in, who has recently appeared in the TV show as Donna’s grandad. There’s circularity.)
Sorry
that
was
very
lumpen.
Really?
This
is