JEWLScholar@MTSU Repository

DEVELOPING A PERSONALIZED ARTICLE RETRIEVAL SYSTEM FOR PUBMED

Show simple item record

dc.contributor.advisor Li, Cen
dc.contributor.author Pitigala, Sachintha Prasad
dc.date.accessioned 2016-08-15T15:03:30Z
dc.date.available 2016-08-15T15:03:30Z
dc.date.issued 2016-06-21
dc.identifier.uri http://jewlscholar.mtsu.edu/handle/mtsu/4984
dc.description.abstract PubMed keyword based search often results in many citations not directly relevant to the
dc.description.abstract user information need. Personalized Information Retrieval (PIR) systems aim to improve the
dc.description.abstract quality of the retrieval results by letting the users supply information other than keywords.
dc.description.abstract Two main problems have been identified for the current PIR systems developed for PubMed:
dc.description.abstract (1) requiring the user to supply a large number of citations directly relevant to a search topic,
dc.description.abstract and (2) producing too many search results, with a high percentage being false positives. This
dc.description.abstract study developed a Personalized Article Retrieval System (PARS) for PubMed to address
dc.description.abstract these problems. PARS uses two main approaches to find the relevant citations to the given
dc.description.abstract information need: (1) Extending the PubMed Related Article (PMRA) feature and (2) Text
dc.description.abstract classification based Multi Stage Filtering (MSF) method. Both approaches require only a
dc.description.abstract small set of citations from the user, and reduce the search output size by eliminating the
dc.description.abstract false-positive citations in the search output. PARS has been experimentally evaluated using
dc.description.abstract the TREC 2005 dataset, and empirically evaluated by subject experts from the biomedicine
dc.description.abstract field. Results show the PARS system is able to produce retrieval results of better quality
dc.description.abstract than the existing PIR systems for PubMed.
dc.publisher Middle Tennessee State University
dc.subject Medical Information Retrieval
dc.subject PubMed
dc.subject Similarity Measure
dc.subject Text Classification
dc.title DEVELOPING A PERSONALIZED ARTICLE RETRIEVAL SYSTEM FOR PUBMED
dc.type Dissertation
dc.contributor.committeemember Seo, Suk
dc.contributor.committeemember Wallin, John
dc.contributor.committeemember Wu, Qiang
dc.thesis.degreelevel Doctoral
dc.thesis.degreegrantor Middle Tennessee State University
dc.subject.umi Computer science
dc.subject.umi Statistics
dc.description.degree Ph.D.
dc.contributor.department Basic & Applied Sciences en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search JEWLScholar@MTSU


Browse

My Account

Statistics