Algorithme de recommandation adaptable pour la personnalisation d'un système mobile
Résumé
This paper introduces a flexible algorithm to derive users' preferences in a mobile and distributed system. Such profiles are implicitly computed from users' spatial and interactive behaviours. A campus visit aid illustrates the benefits of the algorithm within unobtrusive recommender systems. The approach provides a set of profiles (personal, group-based and hybrid) to adapt the presentation of campus services and suit users' immediate needs and interests. A Java-based simulation framework allows designers to customize the model before in situ validation.
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...