Discussion of document retrieval systems and measuring system performance focuses on the upper bounds, or maximum performance, that can be obtained with a system. Topics addressed include bounds for retrieval performance; average search length; average precision; incomplete searches; an asymmetric measure of retrieval performance; and measuring…

Reports on a theoretical model of structured document indexing and retrieval based on the Dempster-Shafer Theory of Evidence. Highlights include passage retrieval, hypertext, relevance, information needs, implementation of the model, an evaluation scheme designed to test the model's effectiveness, and results of experiments that investigated…

Discusses the variety of performance measures available for information retrieval systems, search engines, and network filtering agents. Considers how measures of performance at a point in a search can be formally compared, develops criteria related to document orderings, and discusses equivalent ordering and precision and recall. (Author/LRW)

Evaluates the effectiveness of spelling-correction and string-similarity matching methods in retrieving similar words in a Malay dictionary associated with a set of query words. Describes experiments that showed the best search combination used a stemming algorithm, and calculates retrieval effectiveness and relevant means measures from weighted…

Duality is an important topic in informetrics, often less studied in information retrieval where it relates to the unification or symmetry of queries and documents, search formulation versus indexing, and relevant versus retrieved documents. This article examines duality in information retrieval and highlights its connection with hypergeometric…

Discussion of information filtering (IF) and information retrieval focuses on the use of an artificial neural network (ANN) as an alternative method for both IF and term selection and compares its effectiveness to that of traditional methods. Results show that the ANN relevance prediction out-performs the prediction of an IF system. (Author/LRW)

Discusses relevance judgments in information retrieval; considers the collaborative nature of information retrieval in a group, organization, or societal context; and proposes a method that measures relevance based on group/peer consensus. Reports results of an experiment using this method to compare the search performance of different types of…

Investigates the use of criteria to assess relevant, partially relevant, and not-relevant documents in information retrieval. Analysis revealed 29 criteria used by graduate students when selecting passages that contributed or detracted from a documents' relevance, the two most frequent being content and criteria characterizing the full text…

Addresses the implications of the new Web metalanguage XML for searching on the World Wide Web and considers the future of XML on the Web. Compared to HTML, XML is more concerned with structure of data than documents, and these data structures should prove conducive to precise, context rich searching. (Author/LRW)

Describes a study that explored aspects of successive Dialog searches conducted by intermediaries for information seekers. Results show most successive searches involve some change in search terms and databases, but precision did not necessarily increase and the percentage of relevant items decreased significantly after three searches. (Author/LRW)

A study to determine the value to humanists of a thesaurus integrating free-text terms from the humanities and social sciences found a high degree of overlap, suggesting that such a thesaurus would be useful to scholars in both disciplines. Results also demonstrated that combining controlled vocabulary and free-text term searching yielded more…

Describes specialty or vertical Web search engines that may provide more relevant results for information retrieval. Highlights include regional services, including filtering by domain and custom crawling; language searching; family-safe listings, including the pros and cons of filtering; news searches; and subject-oriented searching. (LRW)

Presents an algorithm for computation of discrimination values in automatic construction of dictionaries for information retrieval. (Author/PF)

Describes a new graphical method of storing and retrieving concept relations of various kinds. (Author/PF)