Create a LocationScoredAboutnessStrategy about cliff-annotator HOT 3 CLOSED

This sounds like a good strategy to me - let's try it and see what we come
back with. After going through all the hand coded articles I felt like the
most important geoinfo was definitely in the headline and first paragraph.

/////////////////////////////
Catherine D'Ignazio
Research Assistant, MIT Media Lab Center for Civic Media
[email protected] || [email protected] || @kanarinka || +1
617 501 2441 || www.kanarinka.com ||
http://civic.mit.edu/blog/kanarinka/

On Fri, Oct 25, 2013 at 12:16 PM, rahulbot [email protected] wrote:

The idea would be to score each country mention. A regular mention would
earn 1 point. A mention in the headline would earn 3 points. The first
mention in the article would earn 2 points. Those number are fairly
arbitrary.

Then the country the article is about would be the one with the most
points.

See #5 (comment)#5 (comment) a motivating example in the hand-coded corpus, plus this idea just sort
of felt right to us in earlier email discussions.

—
Reply to this email directly or view it on GitHubhttps://github.com//issues/6
.

from cliff-annotator.

Catherine why don't you take this one - so you can learn the Java stuff I added. Check out the stuff in the edu.mit.civic.mediacloud.where.aboutness and make your own subclass of AboutnessStrategy in there. Then instantiate that in edu.mit.civic.mediacloud.ParseManager.aboutness and see if it works better.

from cliff-annotator.

ok great! Will try to do before Thursday (finishing writing up my thesis
proposal at the moment)

www.kanarinka.com || [email protected] || 617-501-2441

On Tue, Oct 29, 2013 at 9:57 AM, rahulbot [email protected] wrote:

Catherine why don't you take this one - so you can learn the Java stuff I
added. Check out the stuff in the edu.mit.civic.mediacloud.where.aboutnessand make your own subclass of
AboutnessStrategy in there. Then instantiate that in
edu.mit.civic.mediacloud.ParseManager.aboutness and see if it works
better.

—
Reply to this email directly or view it on GitHubhttps://github.com//issues/6#issuecomment-27304379
.

from cliff-annotator.