doi:10.1016/j.ipm.2003.10.007
Copyright © 2003 Elsevier Ltd. All rights reserved.
Self-organizing maps of Web spaces based on formal characteristics
a Library and Information Science Faculty, University of Extremadura, Alcazaba de Badajoz (Antiguo Hospital Militar), 06071, Badajoz, Spain
b Library and Information Science Faculty, University of Granada, Campus Cartuja, Colegio Máximo, 18071, Granada, Spain
Received 3 April 2003;
accepted 28 October 2003.
Available online 20 December 2003.
References and further reading may be available for this article. To view references and further reading you must
purchase this article.
Abstract
The unceasing growth of electronic information available on the Web has made it indispensable to develop tools to analyse and evaluate its quality. Given the subjectivity underlying most of the qualitative analytical indicators at the present time, we here propose the use of characteristics or indicators of a formal character. We apply Kohonen’s neural networks and study their topological organization in order to analyse how Web spaces behave with respect to these networks’ formal characteristics. The interpretation of the results brings out the underlying structures and relationships in a closed Web environment.
Author Keywords: Neural networks; Self-organizing maps; Formal indicators of quality
Fig. 1. Classification of the vectors of the characteristics (rectangular neighbourhood), showing each characteristic’s winning zone and winning neuron, and the winning neuron of the Web spaces (first 200 of our classification).
Fig. 2. Classification of the vectors of the characteristics (rectangular neighbourhood), showing each characteristic’s winning zone and winning neuron, and the winning neuron of the Web spaces (ranked according to our classification).
Table 1. Formal characteristics

Table 2. Keys of the page characteristics of the Web spaces

Table 3. Properties of the Web spaces grouped into the zones of influence of the formal characteristics
