The experimental best match information retrieval system described is based on serial file organization. Documents and queries are characterized by fixed length bit strings (generated by automatic and manual methods) and character-by-character term match is preceeded by bit string search to eliminate documents which cannot satisfy query.…

An iterative method for information retrieval is presented using searchonyms found from previously retrieved set of documents in query expansion. Large operational bibliographic databases are used to simulate behavior of this method which selects most informative features as searchonyms to be used in query reformulation. Ten references are listed.…

Results of an experimental study of the retrieval effectiveness of computer-recognized citing statements indicate that average recall for eight retrieval requests by search of indexing and abstract text words was 50 percent. Addition of words from citing statements referring to papers to be retrieved increased average recall to 70 percent.…

Implementation of relevance feedback explored here demonstrates feasibility of query reformulation for boolean retrievals from online databases. Improvements to a term prevalence formula used in earlier research are presented, along with experimental results that confirm crucial role of term weights in relevance feedback. Seven references are…

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…

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…

Discusses formulation of value function based on research from modelling, value assessment, human information seeking behavior, and human decision making. The proposed function is incorporated into computer-based fiction retrieval system and evaluated based on ability of individual's value function to discriminate among novels selected, rejected,…

The increasing complexity of evaluating information retrieval (IR) systems is discussed in terms of contributing factors and research methods. Examples are provided from experiments with weighted searching on a front-end system, information-seeking behavior and online catalogs, and the OKAPI experimental retrieval system. (21 references) (LAE)

Considers the meaning of relevance and examines the role that relevance plays in information behavior. Literature on relevance is reviewed, cognitive and dynamic processing approaches to relevance are described, and 12 research questions are presented that address criteria users employ in evaluating information and suggest implications for system…

This overview of the research process for the novice information retrieval (IR) researcher provides guidance on selecting a research question, choosing the type of test, defining variables, developing or using databases, finding and processing queries, assigning treatments to experimental units, collecting and analyzing the data, and presenting…

The approach of J. D. Sneed is used to argue for a distinction between theoretical and nontheoretical (or empirical) entities. Attention is directed toward this approach as an important facility for looking at statistics and for constructing a framework for the correct use of statistical theory in information retrieval experiments. (MBR)

Discusses the problem of determining an adequate sample size for an information retrieval experiment comparing two systems on separate samples of requests. The application of statistical methods to information retrieval experiments is discussed, the Mann-Whitney U Test is used for determining minimum sample sizes, and variables and distributions…

This content analysis of library and information science (LIS) research from 1965 to 1985 was conducted to determine the distribution of topics in research articles and the research methodologies that have been used. Results indicated that information storage and retrieval was the most popular topic and that empirical strategies predominated. (20…

Demonstrates efficiency of preparation of query description using semantic analyser method based on analysis of semantic structure of documents in field of automatic indexing. Results obtained are compared with automatic indexing results performed by traditional methods and results of indexing done by human indexers. Sample terms and codes are…

Describes a fast algorithm for comparing the lists of terms representing documents in automatic classification experiments. Complexity and running time for the algorithm are compared to other procedures, and a short algol-like routine is presented in the appendix. Eight references are included. (Author/BK)