An automatic method for classifying medical researchers into domain specific subgroups
by Cecchetti, Alfred A., Ph.D., UNIVERSITY OF PITTSBURGH, 2009, 162 pages; 3375261

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.
 
AdviserEllen G. Detlefsen
SchoolUNIVERSITY OF PITTSBURGH
SourceDAI/A 70-10, p. , Nov 2009
Source TypeDissertation
SubjectsLibrary science; Health sciences; Information science
Publication Number3375261
Adobe PDF Access the complete dissertation:
 

» Find an electronic copy at your library.
  Use the link below to access a full citation record of this graduate work:
  http://gateway.proquest.com/openurl%3furl_ver=Z39.88-2004%26res_dat=xri:pqdiss%26rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation%26rft_dat=xri:pqdiss:3375261
  If your library subscribes to the ProQuest Dissertations & Theses (PQDT) database, you may be entitled to a free electronic version of this graduate work. If not, you will have the option to purchase one, and access a 24 page preview for free (if available).

About ProQuest Dissertations & Theses
With over 2.3 million records, the ProQuest Dissertations & Theses (PQDT) database is the most comprehensive collection of dissertations and theses in the world. It is the database of record for graduate research.

The database includes citations of graduate works ranging from the first U.S. dissertation, accepted in 1861, to those accepted as recently as last semester. Of the 2.3 million graduate works included in the database, ProQuest offers more than 1.9 million in full text formats. Of those, over 860,000 are available in PDF format. More than 60,000 dissertations and theses are added to the database each year.

If you have questions, please feel free to visit the ProQuest Web site - http://www.proquest.com - or call ProQuest Hotline Customer Support at 1-800-521-3042.