• Aucun résultat trouvé

Visualization and User Control of Recommender Systems

N/A
N/A
Protected

Academic year: 2022

Partager "Visualization and User Control of Recommender Systems"

Copied!
1
0
0

Texte intégral

(1)

Visualization and User Control of Recommender Systems

Julita Vassileva

Department of Computer Science University of Saskatchewan

Saskatoon, SK, Canada julita.vassileva@usask.ca

Abstract

The talk will give an overview of some of the existing approaches for visualizing recommendation mechanisms and eventually allowing users to control them.

Starting with work from the area of open/scrutable learner models in the area of intelligent tutoring systems, through approaches for explaining recommendations to approaches visualizing aspects of collaborative, hybrid and social recommenders, as well as the filter bubble, the talk will be based both on the speakers' own work in this area and on a review of other work and will touch on some philosophical issues about how to evaluate recommendations.

Références

Documents relatifs

In other words preference rating for product Y j” in a sales receipt Z in S C is calculated by combination of feature description of product Y j” and feature description of set

Formal verification methods differ in the types of program models (state machines, Petri nets, labeled transition systems), types of requirements models (software

Explainability; Explanations; Transparency; Dark Patterns; Inter- pretability; Intelligibility; User Control; Intelligent Systems.. ACM

These results allow us to extend the model for personalization in music recommender systems by providing guidelines for interactive visualization de- sign for music recommenders,

The final aim of the experimental language learning and studying platform is to cater to different groups of people, offering a comprehensive online resource that connects

(2) Organizational strategies and structure; (3) Organizational culture (teacher’s atti- tudes towards change and technology); (4) Human resources (teachers’ skills and

In addition, the recent adoption of the Business Process Modeling and Notation (BPMN) standard by the OMG (Object Management Group, the same body that defines and

Specifically, in recommender systems, the exploitation of user personality information has enabled address cold-start situations [25], facilitate the user preference