Bio-linguistic statistical correlations in Pubmed, apparently

In Uncategorized on June 17, 2008 by Alan Lovell Tagged: , ,

e-LiSe (short for “e-Literature Searcher” apparently) is yet another website that interrogates PubMed/MEDLINE. This one “uses PubMed database of scientific abstracts as the source of data and a novel bio-linguistic statistical method (based on Z-score), to discover true correlations, even when they are low-frequency associations”, whatever that means. It “…is also capable of finding names of researchers correlated to the information searched by the user. It can function as a name reference engine, answering questions like ‘who is working on specified subject?’ or ‘what are the coworkers/collaborators of a certain person?'” Well, who can argue with that?

One of my hats is that of managing editor for an academic journal that makes copious use of expert commentary and critique, and as a result I do from time to time spend much of my day looking for such expert commentators. I therefore tried e-LiSe to find frequent authors in a field and, you know what, it was rather helpful. Also, when preparing for searches etc., I think it might well be a useful tool for finding synonyms and related terms.

Give it a whirl. It doesn’t look very pretty, but then it does seem to have been made by a bunch of academic coders who probably rarely see the light. If you’re interested in the technical details behind it (the Z-score etc) then take a look at their recent paper here.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: