I'll keep the next hack night on my radar, this is an interesting project.<br><br><div class="gmail_quote">On Thu, Aug 16, 2012 at 4:56 PM, Nathan Rice <span dir="ltr"><<a href="mailto:nathan.alexander.rice@gmail.com" target="_blank">nathan.alexander.rice@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div class="im">On Thu, Aug 16, 2012 at 4:13 PM, Jesse <<a href="mailto:jessebikman@gmail.com">jessebikman@gmail.com</a>> wrote:<br>
> I don't know how helpful I'd be, but I'd like to at least check out what<br>
> you're doing. I just started programming in Python last month. When could<br>
> this happen? Are you near Chapel Hill?<br>
<br>
</div>I work at UNC. I could demonstrate some stuff at a hack night. I'm<br>
still in the planning stages for most of the stuff; I have the pubmed<br>
extraction code pretty well nailed, and I have a solid outline for the<br>
article disqualification (create a feature vector out of topic and<br>
abstract bigrams, MeSH subject headings and journal, use a SVM<br>
discriminator and manually generate a RoC curve to determine the<br>
cutoff score) but I'm still very up in the air regarding NL extraction<br>
of things like sample size, significance, etc. If you'd like to learn<br>
more I would of course be happy to go over my thoughts on the matter<br>
and we can play around with some code.<br>
<span class="HOEnZb"><font color="#888888"><br>
Nathan<br>
</font></span></blockquote></div><br><br clear="all"><div><br></div>-- <br>Jesse Bikman<br>