Dissertation Information for Zainal Hasibuan
- Zainal Hasibuan
- Library and Information Science
- Indiana University (USA) (1995)
- Stephen P. Harter
- Debora Shaw
- Barry Rubin
- Charles Davis
- Verna Leah Pungitore
MPACT Status: Fully Complete
Title: Document similarity and structure: Using bibliometric methods and index terms as approaches to improving information retrieval performance
Abstract: This study explored the inherent structure of a document collection in an effort to learn more about characteristics that might improve information retrieval performance. The characteristics examined are: descriptors, references (cited documents), and citing documents. Three independent variables were studied: co-descriptor, bibliographic coupling, and co-citation.
A test collection was constructed by searching on a single descriptor "information retrieval" in the CD-ROM version of ERIC, covering the period 1981 through 1985. Descriptors were extracted from ERIC; cited and citing documents associated with the test collection were derived from Social Sciences Citation Index.
The working hypothesis of this study is that similar documents will have similar descriptors, references, and citing documents. Document similarity was measured using simple matching for document pairs, and Jaccard's coefficient for document clusters. A cluster analysis was conducted using the single-link method.
The results showed that there is a linear relationship among the variables. Clusters were formed in the test collection based on each of the variables alone and on the combined variables. A separate evaluation was conducted using a subject expert to judge the relatedness of the documents. The subject expert's evaluations were in agreement with the computation results. The findings of the study suggest viable methods for improving the performance of information retrieval systems.
MPACT Scores for Zainal Hasibuan
A = 0
C = 0
A+C = 0
T = 0
G = 0
W = 0
TD = 0
TA = 0
calculated 2008-01-31 06:08:00
Advisors and Advisees Graph