Reports a study that examined 10 collections of mainly scientific subject areas indexed using Farradane's system of relational indexing. It compared (1) the use of relations, (2) the use of concept types, (3) the cross sections (or shape) of abstracts, and (4) the properties of "nodes." Statistical tables and graphs are included.…

Describes experiments that compared a new method for automatically analyzing semantic structures in text by statistical means with the standard vector space model. Findings indicate that combining both methods improved performance over either alone. The effects of other experimental variables on retrieval performance (term weighting, suffix…

Examines research on the observed values of retrieval effectiveness obtained in searches of files of nearest neighbor document clusters. Results show interdocument similarities used to generate nearest-neighbor clusters are significantly different from randomly generated clusters. (Contains 14 references.) (EAM)

Describes a new effectiveness measure as an alternative to the traditional evaluation measures of recall and precision in information retrieval systems. The statistical approach--which compares two retrieval algorithms--is explained, the information needs of the user are considered, and an experiment with a test collection of abstracts is…

Various methods for calculating and presenting results of information retrieval (IR) evaluation research are discussed, with illustrations from recent laboratory results. Highlights include measures for calculating recall and precision, user needs for high or low level of recall, and comparisons of Boolean and ranked output retrieval. (22…

Describes a citation analysis of physics, engineering, and sociology literature which was designed to determine if there were any differences in conceptual referencing patterns. The research methodology is described and suggestions for further study are offered. (Author/LRW)

Empirical comparisons are made of three statistical sampling methods evaluated for estimating total number of relevant documents in collection for given query: simple random sampling, random sampling which assigns unequal selection probabilities to individual documents in collection, and curve fitting and extrapolation. Nine references and…

Describes study of manual and experimental automated circulation systems in a university library in Nigeria. Data were collected for eight circulation activities in order to calculate the direct labor costs of circulating a book on each system. Automated system's book circulation costs were higher although direct labor costs were less. (MBR)

Examines the use of various statistical techniques for generating domain-oriented multiword vocabulary terms for natural language database systems. Conclusions show the vocabulary clustering effect should be considered when making significance calculations and that a simple ratio of subject matter relative frequency to total sample relative…