Similarity metrics for clustering PubMed abstracts for evidence based medicine

Hassanzadeh, Hamed, Molla, Diego, Groza, Tudor, Nguyen, Anthony and Hunter, Jane (2015). Similarity metrics for clustering PubMed abstracts for evidence based medicine. In: Ben Hachey and Kellie Webster, Australasian Language Technology Association Workshop 2015: Proceedings of the Workshop. Australasian Language Technology Association Workshop, Parramatta, NSW, Australia, (48-56). 8-9 December 2015.

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
Author Hassanzadeh, Hamed
Molla, Diego
Groza, Tudor
Nguyen, Anthony
Hunter, Jane
Title of paper Similarity metrics for clustering PubMed abstracts for evidence based medicine
Conference name Australasian Language Technology Association Workshop
Conference location Parramatta, NSW, Australia
Conference dates 8-9 December 2015
Proceedings title Australasian Language Technology Association Workshop 2015: Proceedings of the Workshop
Publisher ALTA
Publication Year 2015
Sub-type Fully published paper
Open Access Status Not Open Access
ISSN 1834-7037
Editor Ben Hachey
Kellie Webster
Volume 13
Start page 48
End page 56
Total pages 9
Collection year 2016
Language eng
Formatted Abstract/Summary
We present a clustering approach for documents returned by a PubMed search, which enable the organisation of evidence underpinning clinical recommendations for Evidence Based Medicine. Our approach uses a combination of document similarity metrics, which are fed to an agglomerative hierarchical clusterer. These metrics quantify the similarity of published abstracts from syntactic, semantic, and statistical perspectives. Several evaluations have been performed, including: an evaluation that uses ideal documents as selected and clustered by clinical experts; a method that maps the output of PubMed to the ideal clusters annotated by the experts; and an alternative evaluation that uses the manual clustering of abstracts. The results of using our similarity metrics approach shows an improvement over K-means and hierarchical clustering methods using TFIDF.
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ
Additional Notes http://www.alta.asn.au/events/alta2015/proceedings/

 
Versions
Version Filter Type
Citation counts: Google Scholar Search Google Scholar
Created: Fri, 11 Mar 2016, 14:46:55 EST by Anthony Yeates on behalf of School of Communication and Arts