HTML page representation through their links and its application to information retrieval

Authors

  • José Luis Alonso Berrocal Departamento de Informática y Automática, Facultad de Traducción y Documentación, Universidad de Salamanca, España
  • Carlos García Figuerola Paniagua Departamento de Informática y Automática, Facultad de Traducción y Documentación, Universidad de Salamanca, España
  • Ángel Francisco Zazo Rodríguez Departamento de Informática y Automática, Facultad de Traducción y Documentación, Universidad de Salamanca, España

DOI:

https://doi.org/10.54886/scire.v5i2.1118

Abstract

The most habitual systems in Information Retrieval are based both on getting a homogeneous and easily processed representation of documents and searches, and on the subsequent calculation of some function that expresses the degree of similarity between a given search and each one of the documents in a collection. Generally, such representations take the words or terms that appear in the documents as base. Web pages, however, contain hyperlinks, which suggests the possibility of representing such pages as a function of hyperlinks, instead of terms. We describe an exploratory experiment carry out to estimate the viability of this hypothesis. The results of this experiment suggest that hyperlinks can be applied advantageously in the representation of web pages, but it is also necessary to define and apply corrective mechanisms.

Downloads

Download data is not yet available.

Published

1999-06-01

How to Cite

Alonso Berrocal, J. L., García Figuerola Paniagua, C., & Zazo Rodríguez, Ángel F. (1999). HTML page representation through their links and its application to information retrieval. Scire: Knowledge Representation and Organization (ISSNe 2340-7042; ISSN 1135-3716), 5(2), 91–98. https://doi.org/10.54886/scire.v5i2.1118

Issue

Section

Articles

Most read articles by the same author(s)

1 2 > >>