The effects of transparency on trust in and acceptance of a content-based art recommender

• DOI: 10.1007/s11257-008-9051-3
• Publication Date: 2008-08-19T09:31:07Z
• Authors: Henriette Cramer; Vanessa Evers; Satyan Ramlal; Maarten van Someren; Lloyd Rutledge; Natalia Stash; Lora Aroyo; Bob Wielinga
• Keywords: Content (measure theory)

The increasing availability of (digital) cultural heritage artefacts offers great potential for increased access to art content, but also necessitates tools help users deal with such abundance information. User-adaptive recommender systems aim present their content tailored interests. These try adapt the user based on feedback from which artworks he or she finds interesting. Users need be able depend system competently and find that are most interesting them. This paper investigates influence transparency trust in acceptance content-based systems. A between-subject experiment (N = 60) evaluated interaction three versions a domain. provides interest them, ratings other artworks. Version 1 was not transparent, version 2 explained why recommendation had been made 3 showed rating how certain would user. Results show explaining recommendations. Trust itself improved by transparency. Showing did acceptance. number guidelines design domain have derived study's results.