Resumen: El problema de la recuperación de información en la web se puede plantear desde diferentes puntos de vista, con mecanismos como la reali-mentación por relevancia, la utilización de tesauros, el estudio de los hiper-enlaces, o la aplicación de redes neuronales, entre otros. Todos estos meca-nismos se aplican sobre grandes bases de datos construidas a partir de la exploración previa de sectores más o menos amplios de la web. La experien-cia ha demostrado que la precisión de estos sistemas es baja, y la exhaustivi-dad está relativizada al sector explorado. Existe sin embargo otra aproxima-ción al problema que pretende obtener resultados mucho más precisos, aun-que sin perseguir altas tasas de exhaustividad, basándose en el uso de agen-tes inteligentes que rastreen la red según las necesidades informativas del usuario. Se indican las características de los agentes y se analizan algunas de las propiedades y habilidades deseables para aquellos agentes dedicados a la recuperación de información en la web. Palabras clave: Recuperación de información, World Wide Web, Agentes. Abstract: The problem of information retrieval in the Web can be raised from different points of view, with mechanisms like the feedback by relevance, the use of thesauri, the study of the hyperconnections, or the application of neu-ronal networks, among others. All these mechanisms are applied on great data bases constructed from the previous exploration of more or less broad sectors of the Web.The experience has demonstrated that the precision of these systems is low, and the recall is relativized to the explored sector. Another approach to the problem tries to obtain much more precise results, although without persecuting discharges rates of recall, and is based on the use of intelligent agents who track the network according to the informative needs of the user. The characteristics of the agents are indicated and some of the properties and desirable abilities for those agents dedicated to the information retrieval in the Web are analyzed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.