Priors for Diversity and Novelty on Neural Recommender Systems

• Alfonso Landin ^[1] ; Daniel Valcarce ; Javier Parapar ^[1] ; Álvaro Barreiro
  1. [1] Universidade da Coruña

     Universidade da Coruña

     A Coruña, España

     
• Localización: XoveTIC 2019: The 2nd XoveTIC Conference (XoveTIC 2019), A Coruña, Spain, 5–6 September / Alberto Alvarellos González (ed. lit.), Joaquim de Moura (ed. lit.), Beatriz Botana Barreiro (ed. lit.), Javier Pereira-Loureiro (ed. lit.), Manuel Francisco González Penedo (ed. lit.), 2019, ISBN 978-3-03921-444-0
• Idioma: inglés
• Enlaces
  • Texto Completo Libro (pdf)
• Resumen

  • PRIN is a neural based recommendation method that allows the incorporation of item prior information into the recommendation process. In this work we study how the system behaves interms of novelty and diversity under different configurations of item prior probability estimations. Our results show the versatility of the framework and how its behavior can be adapted to the desiredproperties, whether accuracy is preferred or diversity and novelty are the desired properties, or how a balance can be achieved with the proper selection of prior estimations.