User preferences, query and document categorization, three important variables in relevance calculation

Authors

Abstract

 

The quality of an information retrieval system depends largely on the satisfaction degree of users with the results obtained when executing a query, so it is essential to design processes that store the preferences patterns of each of them and vary the way in which the results are shown taking into account the specific characteristics of each user. The objective of this article was to present an algorithm for calculating the relevance of the documents provided to users, which used the variables: the user's search profile, the category of the documents and the category of the query as parameters, to customize the results provided by the search engine to the users. In addition, it used as impulse factors the degree of predominance of a search category in the user's profile and the categories to which the document belongs. To validate the algorithm, precision and recall metrics were applied to check that the results obtained are relevant to users.

Author Biographies

Paúl Rodríguez Leyva, Universidad de las Ciencias Informáticas

Jefe de departamento de Soluciones Informáticas para Internet, especialista en recuperación de información y sistemas de recuperación de información.

Hubert Viltres Sala

Profesor Auxiliar jefe de año en la Facultad 1

Vivian Estrada Sentí, Universidad de las Ciencias Informáticas

Profesora Titular, Metodóloga.

Yennifer Delgado mesa, Universidad de las Ciencias Informáticas

Máster en Informática Avanzada

Published

2020-05-24

How to Cite

1.
Rodríguez Leyva P, Viltres Sala H, Febles JP, Estrada Sentí V, Delgado mesa Y. User preferences, query and document categorization, three important variables in relevance calculation. Rev. cuba. inf. cienc. salud [Internet]. 2020 May 24 [cited 2025 Feb. 7];31(2). Available from: https://acimed.sld.cu/index.php/acimed/article/view/1396

Issue

Section

Artículos Originales

Most read articles by the same author(s)