Biomedical subjects

Yuri Kagolovsky

Publications and source records attributed to Yuri Kagolovsky.

5 recordsLinked to original sources

PubMed2004

Introducing a conceptual information retrieval (IR) framework.

This is the third in the series of the articles on an application of the systems analytic approach to evaluation of information retrieval (IR). Previously terminological and evaluation problems associated with IR were identified, and it was proposed that the systems analytic approach can provide solutions to these problems. Here, after the general discussion of a systems approach, different attempts to introduce this approach into IR are presented and critiqued: modelling of IR, identifying boundaries of a system under evaluation, identifying variables under investigation; and creating evaluation frameworks. On the basis of the critique of this work, the authors present their proposal for a solution: first the IR components, their boundaries and relationships are identified, and then the two models of IR are introduced. One of the models addresses components of the IR process and relationships between them, the second one is the process model of IR.

Canada↗

PubMed2003

Current status of the evaluation of information retrieval.

This is the second in the series of the articles on an application of the systems analytic approach to evaluation of information retrieval (IR). In the previous article a historical overview of IR was presented and existing terminological problems associated with IR were identified and discussed. In the presented article the current status of IR evaluation is summarized, and different evaluation approaches are discussed. The Cranfield evaluation model and the most often used relevance-based measures of recall and precision are explained, and their problems are presented. Possible evaluation alternatives to the Cranfield model are discussed, and the case for a systems analytic approach to IR is summarized.

Abstracting and Indexing↗

PubMed2003

Terminological problems in information retrieval.

This is the first in the series of the papers on an application of the systems analytic approach to evaluation of information retrieval (IR). At the beginning, the importance of consistent terminology in information retrieval is discussed, and different definitions of "information retrieval" and "IR system" are presented. The importance of identifying boundaries of the IR system for clarifying terminological differences is discussed. The terminological problems in IR are summarized, and some of the existing approaches to their solution are identified. A historical overview of IR research is presented in order to explain the existing terminological differences and to create a common basis for a discussion of evaluation approaches to IR.

Databases, Bibliographic↗

PubMed2002

A new method for matching a document to potential users' information needs.

This paper explores approach to finding out how the information needs that a document can address can be captured. This is important in order to improve indexing strategies applied to document collections. We propose and implemented a cognitive science approach, the "jeopardy game" method of evaluation combined with "think aloud" analysis. The results of the demonstration study are presented and discussed. Some possible improvements to the method for matching a document to potential users' information needs are identified.

Information Storage and Retrieval↗

PubMed2002

Cluster analysis of Wisconsin Breast Cancer dataset using self-organizing maps.

This work deals with multidimensional data analysis, precisely cluster analysis applied to a very well known dataset, the Wisconsin Breast Cancer dataset. After the introduction of the topics of the paper the cluster analysis concept is shortly explained and different methods of cluster analysis are compared. Further, the Kohonen model of self-organizing maps is briefly described together with an example and with explanations of how the cluster analysis can be performed using the maps. After describing the data set and the methodology used for the analysis we present the findings using textual as well as visual descriptions and conclude that the approach is a useful complement for assessing multidimensional data and that this dataset has been overused for automated decision benchmarking purposes, without a thorough analysis of the data it contains.

Breast Neoplasms↗