The current state of information retrieval (IR) evaluation is reviewed with criticisms directed at the available test collections and the research and evaluation methodologies used, including precision and recall rates for online searches and laboratory tests not including real users. Automatic text retrieval systems are also discussed. (32…

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…

Discusses approaches to the integration of query-based information retrieval and browsing in a hypertext network. A prototype system developed to evaluate the proposed approach in terms of retrieval effectiveness and search efficiency is presented, and design and implementation issues concerning the prototype are considered. (30 references) (EA)

Describes a simulation method for estimating recall and fallout in a document retrieval system. Earlier research on simulating document retrieval systems is reviewed, examples are presented of the current method, a probabilistic justification of the method is given, theoretical concerns dealing with retrieval precision are discussed, and further…

This study of an individual information user with a real information problem examined the relevance judgment process using bibliographic records and full-text documents. Results provide a basis for understanding the judgment process in information searching. Deselection of items and the associated application of judgment criteria provide insight…

Explores metasearch engine (metasearch engines search several Web indexes and/or directories and/or Usenet and/or specific Web sites) efficiency and problems, focusing on four engines in specific: Dogpile, Cyber411, Internet Sleuth, and Metacrawler. Concludes that because no engine has precisely the same coverage as another, the searcher using a…

Describes a study conducted in the Netherlands that examined the effect of a user's World Wide Web experience on the search process, which consists of locating an appropriate Web site and retrieving relevant information from that site. Discusses implications for training and supporting student searchers and proposes future research. (Author/LRW)

In information science, it is important to consider the nature and meaning of theories of aboutness, subject analysis and related concepts, which are closely related to theoretical and metatheoretical issues in information retrieval (IR). A theory of IR must specify which concepts should be regarded as synonymous concepts and explain how the…

Summarizes empirical results reported earlier on relations between students' problem stages (mental model) in writing research proposals for a masters' thesis and the information sought, choice of search terms, and relevance assessments; refines Kuhlthau's model of the information search process; and proposes a theory of a task-based information…

Discusses results from recent relevance research with implications for information professionals. The studies show that beyond the usual concern with high relevance and non-relevance judgments, partially relevant judgments by users are important. Calls for the adoption of a more complex view of human relevance judgments in the education and…

Describes the University of California at Berkeley's participation in the TREC (Text Retrieval Conference) interactive track experiments. Highlights include results of searches on two systems, Cheshire II and ZPRISE; system design goals and implementation; precision and recall results; search questions by topic and system; and results of…

Examines the history, structure, and search capabilities of Internet search tools AltaVista and Yahoo. AltaVista provides relevance-ranked feedback on full-text searches. Yahoo indexes Web "citations" only but does organize information hierarchically into predefined categories. Yahoo has recently become a publicly held company and…

Discussion of the use of Latent Semantic Indexing to determine relevancy in information retrieval focuses on statistical regression and Bayesian methods. Topics include keyword searching; a multiple regression model; how the regression model can aid search methods; and limitations of this approach, including complexity, linearity, and…

Uses a reliability framework to examine the role that relevance judgments play in quantitative information retrieval (IR) performance measurement with an eye toward issues introduced by Internet IR. Argues that a theoretical basis for reliable measurement is possible if the relevance yardstick is reconsidered in light of recent research and if the…

Reports on a continuing investigation of intertextual networks. Describes how intertextual networks can be modeled as directed graphs and extends this to matrix representations. Discusses topological index values of these networks and speculates how topological index values might be used in the estimation of retrieval values in information…