Hi,
I would like to request a luxembourgish version of Wikipedia. First of all,
it's the language of my country, Luxembourg, and second, luxembourgish is
only spoken in my country and still not by the whole population as we have
42% foreigners who mostly speak french. To keep the language alive, I think
it would be a good idea to have a wikipedia in lux.
Folks,
For my own purposes, I have created an RPM of the mediawiki-1.2.6
stable download.
If anyone would like to poke at it and make suggestions, it can be
found at :-
ftp://ftp.wizzy.com/pub/wizzy/rpms/mediawiki-1.2.6-2wiz.noarch.rpmftp://ftp.wizzy.com/pub/wizzy/SRPMS/mediawiki-1.2.6-2wiz.src.rpm
I want to do this for schools install, and the web interface, though
very nice, does not fit in with the 'fire and forget' nature of RPMs.
I run sed over the (unmodified) sql scripts in /maintenance to do
the initial database setup.
It will still need a snapshot loaded.
To load a snapshot of wikipedia, try this :-
bzip2 -d -c 20040327_cur_table.sql.bz2 | mysql -u wikiuser --password=wiki:user wikidb
Cheers, Andy!
http://wizzy.org.za/
Europe will over the next years install a GPS-like positioning system
called Galileo. The German list got a suggestion to include coordinates
in the form of
[[Geo:-13°23'+45°2'23'']]
or similar for locations. A future GPS/Galileo PDA/smartphone could then
reverse-lookup what wikipedia has about the current location. (This is
kind of a PR gag, but still...)
IMHO that brings us back to the map system we already discussed to death ;-)
Seriously, such markup could link to a special page with multiple functions:
* Show it on a map
* List wikipedia locations nearby
and others I can't think of right now.
Should we
a) include such a syntax?
b) wait for a "real" map system to emerge, or just do this now and
convert later?
Magnus
Here are some responses to the issues raised so far about using "influence
links" to find information in Wikipedia. (original post here
http://mail.wikipedia.org/pipermail/wikipedia-l/2004-July/015988.html)
First, Hemanshu brings up a potential POV problem: "do we want endless
arguments over whether America influenced the Taliban; George Bush
influenced oil markets; oil influenced Gulf war.... to name a few?"
To avoid this, there is one rule: an influence must already be present in
the article to be made an "influence link". This way, only assertions
that have already passed the wiki test are admissible. The key idea is
that influence links don't add new information to the article. Rather,
they make explicit the influences that are already present in the article.
Then, they can be used to analyze relationships among articles (more on
possible uses for this system, below).
On another issue, Austin pointed out: "...for it to be useful for any kind
of analysis we would have to work out a system to show the extent and type
of relationships involved."
The way around this, is to give users the burden of describing the type of
each influence link. Users would include a small description next to each
influence link. For example, the article on Copernicus reads:
"His theory about the Sun as the center of the solar system, turning over
the traditional [[geocentric theory]] (that placed Earth at the center of
the Universe), is considered one of the most important discoveries
ever...."
On Copernicus' "influences" page, one influence link would look like this:
Copernicus influenced:
- [[geocentric theory]], Copernicus turned over the traditional
geocentric theory.
If a user searches for a path of influences between Article "A" and
Article "C", the result would look like:
- [[A]] influenced [[B]]. Short description of how A influenced B.
- [[B]] influenced [[C]]. Short description of how B influenced C.
In the results, each influence link would have a checkbox next to it,
allowing the user to easily glance through and un-check any influence
links that aren't of the type he/she is looking for. Then the user could
re-run the search, with the un-checked influence links filtered out.
Austin also rightly notes that if there aren't enough influence links,
they can't be strung together to show complex paths of influence. But,
since the influences are already in the articles, I don't think it would
bee too much trouble for users to make them explicit by simply listing
them under the influence tab.
Hemanshu brings the discussion back to the mission of Wikipedia by asking
what all of this has to do with making an encyclopedia. In response, I
say that an encyclopedia needs two things: good content, and a structure
for finding the content. With conventional encyclopedias, readers found
articles in only one way: paging through, alphabetically. Today,
Wikipedia uses a search engine. Or, if you'd rather browse by topic, you
can navigate your way through Wikipedia's categories. The more ways you
can find information in an encyclopedia, the more useful it is, which is
why cross-referencing with hyperlinks in articles is so powerful. None of
these tools affect the way articles are written--just how they are found.
An "influence map" would be one more tool for finding information that
allows you to browse through artiles by tracing their influences, and
searching for influence paths between articles. Also, by skimming an
article's influence page, to see its outgoing/ingoing influence links, you
can quickly put the article in context.
Moreover, influence links will create an incentive for users to contribute
more to the Wikipedia as a whole. For example, if you are a contributor
to the Copernicus article, not only do you want to make sure that the
Copernicus article is high-quality and NPOV, but you'll want to make sure
that articles on subjects which claim to have influenced Copernicus do so
accurately with a NPOV. An influence map for each article would allow you
to quickly see who is claimed to be an influence on Copernicus, allowing
you to correct mistakes or POVs in articles that you might not otherwise
edit. With more people editing more articles, the whole Wikipedia becomes
richer.
Does that fill the gaps? Any more thoughts?
Abe
Ray Saintonge wrote:
>>What *would* be cool, and might just be a different implementation of
>>exactly what you have in mind, would be a tool to find all the
>>(reasonably short) click-paths between any two concepts. I mean, now
>>that I selected the article titles randomly, I actually wonder how
>>many clicks it takes to get from Marie Antionette to Michael Jordan.
>>And what's intervening?
>>
>Over a year ago I raised the possibility of tracing every article back
>to the Main Page. None in my random sample was more than five links
>away. Thus if you trace Marie Antoinette and Michael Jordan back to the
>Main Page, the sum of their links will be a maximum distance. :-)
>
Maybe I'm misunderstanding you, but I don't think that last statement is
correct. The number of links required to travel in one direction is not
necessarily the same as the number required in the opposite direction.
In this case, the paths from A to B and from A to C do not necessarily
tell us anything about the path from B to C. Although if A is the Main
Page, you can always cheat and use any of the navigation links that go
there.
--Michael Snow
Jimmy (Jimbo) Wales wrote:
>What *would* be cool, and might just be a different implementation of
>exactly what you have in mind, would be a tool to find all the
>(reasonably short) click-paths between any two concepts. I mean, now
>that I selected the article titles randomly, I actually wonder how
>many clicks it takes to get from Marie Antionette to Michael Jordan.
>And what's intervening?
>
>Basically, this doesn't need a special type of "influence map", but
>rather just an analysis of existing links.
>
Check out [[Wikipedia:Six degrees of Wikipedia]]. It's just for fun, and
we'd have to create a specific search function to do it automatically,
but that's basically what you're talking about.
--Michael Snow
I thought I should act on Andre's suggestion at wikide-l that this
proposal be discussed globally, so I forwarded and translated his post
in my previous message. If you take a look at the test upload form, it's
in German, but if any non-German-speakers have questions about it, feel
free to ask. Now for my comments.
Field 6, as with the current form, asks the user to confirm that the
copyrightholder agrees to the licensed use. Field 4 asks who created the
image and/or what is the source. Field 5 asks you to choose a license;
the options provided are GFDL, CC-by, CC-by-sa, and unknown. As
indicated, if you choose unknown, you get a message first about our
policy for using licensed images. All of these fields are required.
I think Andre has done excellent work, and this upload form should be
implemented on all Wikipedias as quickly as possible. I actually care
less about making users input licensing information, but as I've said
repeatedly, we absolutely need an upload form that *requires* source
information. This matters even more for Wikipedias that, unlike the
German Wikipedia, allow fair use images. According to international law,
we *must* provide source information in order to have copyrighted images
under fair use (or as the Berne Convention calls it, fair practice).
--Michael Snow
Andre Darmochwal (de:Benutzer:Sansculotte) wrote:
>Hallo Ihr,
>
>nachdem schon seit längerem über die Defizite unseres Bild-Uploades
>gemeckert wird, insbesondere die Faulheit vieler Benutzer, eine Lizenz
>und weitere Bildinfos einzutragen und dsa Hinterherräumen ziemlich
>aufwendig ist, habe ich mal den Versuch gewagt und ein neues
>Upload-Formular entworfen.
>
>Schaut es Euch mal an unter http://www.ru-info.de/upload_neu.htm und
>gebt mir Euer Feedback.
>
>In den Feldern 4 (Urheber), 5 (Lizenz) und 6 (Bestätigung) muß etwas
>eingetragen sein, sonst kann der Upload nicht gestartet werden. Gibt
>der Benutzer bei "Lizenz" "unbekannt/weiß nicht" an, erhält er
>folgende Meldung:
>
>http://www.ru-info.de/upload_lizenz.htm
>
>Bleibt der Uploader dann bei "unbekannt/weiß nicht", wird das
>hochgeladene Bild automatisch in die [[Kategorie:Bilder ohne
>Lizenzangabe]] einsortiert.
>
>Die gemachten Angaben werden dann zu den Bildinformationen ergänzt:
>
>http://www.ru-info.de/upload_ergebnis.htm
>
>Nach Auskunft von gwicke sollte die Implementation des Uploadformulars
>mit zwei bis drei Stunden Arbeitsaufwand machbar sein. Die Frage ist,
>ob diese Formular nur für die deutschsprachige Wikipedia eingerichtet
>werden soll/kann oder für alle Wikipedias. Im letzteren Fall müsste
>das Form erst über wikipedia-l abgestimmt werden.
>
>Lieber Gruß, Andre
>
Translation follows:
Hello all,
After a lengthy discussion about the weaknesses of the image upload
form, particularly in light of the effort required to clean up after
users who are too lazy to provide licensing and other information, I
have tried my hand at creating a new upload form.
Take a look at http://www.ru-info.de/upload_neu.htm and give me your
feedback.
Fields 4 (originator), 5 (license) and 6 (confirmation) must be filled
in for the upload to work. If the user enters "unknown" in the license
field, he gets the following message first:
http://www.ru-info.de/upload_lizenz.htm
If the uploader sticks with "unknown" as the license, the uploaded image
is automatically added to [[Category:Images without license information]].
The information in these fields is added to the image description page
as shown here:
http://www.ru-info.de/upload_ergebnis.htm
According to gwicke, it should only take about two or three hours of
work to implement the new upload form. The question is whether this form
can/should be implemented only for the German Wikipedia, or for all
Wikipedias. In the latter case, the form would need to be approved on
wikipedia-l first.
Greetings, Andre
Wikipedia has proven itself as an effective process for creating
encyclopedia articles. But, there's an easy way to give Wikipedia the
ability to to show causal relations among articles.
For example, all articles could have a tab called "influences". In the
case of the article on Copernicus, users would be free to list hyperlinks
to other articles that complete the sentence
"Copernicus influenced_____."
and articles that complete the sentence
"______influenced Copernicus".
If users did this for many articles, then a network of causation would
emerge, where the nodes of the network are articles and the links are
"influences". This network could be exploited through a search tool that
finds paths of articles between article A and B.
Such a tool would allow for a fascinating study of history. For instance,
Wikipedia currently has an article on the Cold War and an article on the
Attacks on Sept. 11. But, what if you want to see if there's a causal
relationship between the two events? Neither article mentions the other,
and rightly so, since any causal relation between them is too indirect for
the scope of an encyclopedia article. Also, you won't find one article
titled "How the Cold War Influenced 9/11" because encyclopedias typically
provide information that fills the middle space of the spectrum between
history books on one end, and the daily newspaper on the other. This
question would usually be a question for history, because normal methods
of tackling such questions require: analysis and time.
But the system I describe above can compress the analysis. Each
influence-link between articles would be one tiny piece of
analysis between events that happpened close together in time. By drawing
a path through these small links of analysis and time, you can connect
events that happen farther apart in time, thereby automating the analysis.
There are a lot of other uses of this kind of "influence
mapping". And, you could get a lot of fun data to play with, as
well. But, that's the main idea I wanted to throw out. Any thoughts?
Abe
May I suggest that next time we are slashdotted,
someone please add a highly visible link at the TOP of
the main page, at least on the english wikipedia, for
say 2 or 3 days, so that perhaps some visitors feel
like making a small donation ?
The events are very demanding on servers, last week,
we were all slowed down a lot for 2 days, so visitors
might understand the need for more hardware.
Besides, given the number of discussions last week on
slashdot, about donation issues, that is perhaps best
to show clearly where donations could be made :-)
So, slashdot events would be beneficial both in terms
of contributors and in terms of revenue ?
__________________________________
Do you Yahoo!?
New and Improved Yahoo! Mail - Send 10MB messages!
http://promotions.yahoo.com/new_mail