Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

AN AUTOMATIC METHOD FOR CLASSIFYING MEDICAL RESEARCHERS INTO DOMAIN SPECIFIC SUBGROUPS

Cecchetti, Alfred A (2009) AN AUTOMATIC METHOD FOR CLASSIFYING MEDICAL RESEARCHERS INTO DOMAIN SPECIFIC SUBGROUPS. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

[img]
Preview
PDF
Primary Text

Download (1MB) | Preview

Abstract

Objective:This dissertation developed an automatic classification procedure, as an example of a novel tool for an informationist, which extracts information from published abstracts, classifies abstracts into their "fields of study," and then determines the researcher's "field of study" and "level of activity." Method: This dissertation compared a domain expert's method of classification and an automatic classification procedure on a random sample of 101 medical researchers (derived from a potential list of 305 medical researchers) and their associated abstracts. Design: The study design is a retrospective, cross-sectional, inter-rater agreement study, designed to compare two classification methods (i.e., automatic classification procedure and domain expert). The study population consists of University of Pittsburgh, School of Medicine, Department of Medicine (DOM) professionals who (1) have published at least one article listed in PubMed® as first or last author and/or (2) are the primary investigator for at least one grant listed in CRISP.Main outcome measures: Three outcome measures were derived from the domain expert's versus automatic categorization procedure: (1) an abstract's "field of study," (2) a researcher's "field of study" and (3) a researcher's "level of activity and field of study." Results: Kappa showed moderate agreement between automatic and domain expert classification for the abstracts' "field of study" (Kappa = 0.535, n = 504, p < .000). Kappa showed moderate agreement between automatic and domain expert classification of the researcher's "field of study" (Kappa = 0.535, n = 101, p < .000). Kappa showed good agreement between automatic and domain expert classification of the researcher's "level of activity and field of study" (Kappa = 0.634, n = 101, p < .000). Conclusion: The study suggests that an automatic library classification procedure can provide rapid classification of medical research abstracts into their "fields of study." The classification procedure can also process multiple abstracts' "fields of study" and classify their associated medical researchers into their "field of study" and "level of activity and field of study." The classification procedure, used as a tool by an informationist, can be used as the basis for new services.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Cecchetti, Alfred Acecch@pitt.eduCECCH
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairDetlefsen, Ellen G
Committee MemberBranch, Robert A
Committee MemberKoshman, Sherry
Committee MemberCarbo, Toni
Date: 7 May 2009
Date Type: Completion
Defense Date: 20 April 2009
Approval Date: 7 May 2009
Submission Date: 30 April 2009
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Institution: University of Pittsburgh
Schools and Programs: School of Information Sciences > Library and Information Science
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: Classification; Medical
Other ID: http://etd.library.pitt.edu/ETD/available/etd-04302009-113137/, etd-04302009-113137
Date Deposited: 10 Nov 2011 19:43
Last Modified: 15 Nov 2016 13:43
URI: http://d-scholarship.pitt.edu/id/eprint/7745

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item