[Wikipedia-l] Showing causation among articles

Tue Jul 13 23:00:07 UTC 2004

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