Publication: Explicaciones para un recomendador de música basadas en datos enlazados
Loading...
Official URL
Full text at PDC
Publication Date
2020
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Citations
Exportar
Abstract
Los sistemas de recomendación proporcionan a los usuarios opciones seleccionadas en base a sus preferencias, aportándoles una forma cómoda y rápida de encontrar elementos de interés. Para que este proceso sea efectivo, sin embargo, el usuario debe comprender las recomendaciones y confiar en el sistema para encontrar lo que busca. Esta confianza puede lograrse mediante el uso de explicaciones, que son una forma intuitiva de justificar la elección de las recomendaciones de forma comprensible para el usuario.
Este trabajo busca enriquecer las explicaciones para un recomendador de música gracias a los datos enlazados. Se hará un estudio de esta tecnología y las formas en que puede aplicarse al ámbito de los sistemas de recomendación y se demostrará de forma práctica con el desarrollo del prototipo de una aplicación que obtenga y muestre explicaciones para el recomendador mencionado.
Recommender systems provide users with choices based on their preferences, providing a convenient and quick way to find items of interest. For this process to be effective, however, the user must be able to understand the recommendations and trust the system to find what they are looking for. This confidence can be achieved through the use of explanations, which are an intuitive way to justify the choice of recommendations in a way that is understandable to the user. In this project we want to enrich the explanations for a music recommender using Linked Data. A study of this technology and the ways in which it can be applied to the scope of the recommendation systems will be made and demonstrated in a practical way with the development of the prototype of an application that obtains and shows explanations for the above-mentioned recommended.
Recommender systems provide users with choices based on their preferences, providing a convenient and quick way to find items of interest. For this process to be effective, however, the user must be able to understand the recommendations and trust the system to find what they are looking for. This confidence can be achieved through the use of explanations, which are an intuitive way to justify the choice of recommendations in a way that is understandable to the user. In this project we want to enrich the explanations for a music recommender using Linked Data. A study of this technology and the ways in which it can be applied to the scope of the recommendation systems will be made and demonstrated in a practical way with the development of the prototype of an application that obtains and shows explanations for the above-mentioned recommended.
Description
Trabajo de Fin de Grado en Ingeniería Informática, Facultad de Informática UCM, Departamento de Ingeniería del Software e Inteligencia Artificial, Curso 2019/2020