A comparative evaluation of results in terms of recall and precision from queries submitted to systems with automatic and manual subject indexing. Differences were attributed to query formulation. The effectiveness of automatic indexing was found equivalent to manual indexing. (Author/KP)

Presents two partitioning methods for signature files and a method of fast weight computation to implement a document ranking strategy. Storage requirements, number of disk accesses, and processing time for these methods are compared with two other access methods. Merits of the partitioning methods are summarized. (20 references) (MES)

Discusses the PRECALL, PRR (probability of relevance given retrieval), and EP (expected precision) approaches for dealing with the problem of weak ordering in information retrieval systems. Findings of two experiments comparing evaluation results obtained by PRR and EP are reported. Several mathematical formulas and proofs are included. (20…

Compares two methods of information retrieval--one that rates documents according to a query and another that uses relevant documents to find further relevant documents (i.e., neighboring documents). Highlights include experiments at the National Library of Medicine; feedback; vector cosine retrieval; and a measure of retrieval effectiveness…

Explains an experiment in text-searching retrieval for cancer questions which developed and used computer procedures (via human simulation) to select search words from medical dictionaries. This study is based on an earlier one in which search words were humanly selected, and the recall results of the two studies are compared. (Author/LRW)

Summarizes the best known methods of using the signature file access method as a storage structure in information retrieval in nonbusiness applications of multimedia data. The relationships between application area, type of data, and signature file organization are emphasized. Results are summarized in a selection guide. (Contains 26 references.)…

Investigates document ranking methods in thesaurus-based Boolean information retrieval systems and proposes a new thesaurus-based ranking algorithm called the Extended Relevance algorithm. Performance comparisons are made between the Extended Relevance algorithm and previous thesaurus-based ranking algorithms. (Contains 20 references.) (LRW)

Discussion of search strategies in information retrieval systems focuses on the implementation of document ranking based on inverted files. Highlights include descriptions of three heuristic methods for implementing a weighting strategy and a comparison of two methods for estimating retrieval accuracy, including document movement and linear…

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 an investigation of the use of document components, such as terms, sentences, and whole documents, for indexing and retrieval. A number of probabilistic similarity measures based on document components are studied, as well as a new method of handling probability estimations involving small sample sizes. (24 references) (Author/CLB)

Describes three models for probabilistic indexing, all based on the Darmstadt automatic indexing approach, and presents experimental evaluation results for each. The discussion covers the improved retrieval effectiveness of probabilistic indexing over binary indexing, and suggestions for using this automatic indexing method with free text terms.…

Describes rough sets theory and discusses the advantages it offers for information retrieval, including the implicit inclusion of Boolean logic, term weighting, ranked retrieval output, and relevance feedback. Rough set formalism is compared to Boolean, vector, and fuzzy models of information retrieval and a small scale evaluation of rough sets is…

Reports information retrieval experiments comparing the performance of a probabilistic retrieval model that incorporates interdocument links with the simpler spreading activation strategy. Results indicated that the overall improvement obtained by including hypertext links in the retrieval model was low. (30 references) (EA)

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…

Summarizes the similarities between classification systems for catalog selection and information retrieval systems, and discusses system characteristics that allow the use of measures such as recall and precision in system evaluation. (27 references) (Author/CLB)