Each to his own: how different users call for different interaction methods in recommender systems

B.P. Knijnenburg, N.J.M. Reijmer, M.C. Willemsen

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

109 Citations (Scopus)
1 Downloads (Pure)


This paper compares five different ways of interacting with an attribute-based recommender system and shows that different types of users prefer different interaction methods. In an online experiment with an energy-saving recommender system the interaction methods are compared in terms of perceived control, understandability, trust in the system, user interface satisfaction, system effectiveness and choice satisfaction. The comparison takes into account several user characteristics, namely domain knowledge, trusting propensity and persistence. The results show that most users (and particularly domain experts) are most satisfied with a hybrid recommender that combines implicit and explicit preference elicitation, but that novices and maximizers seem to benefit more from a non-personalized recommender that just displays the most popular items.
Original languageEnglish
Title of host publicationRecSys '11 Proceedings of the fifth ACM International Conference on Recommender Systems, 23-27 October 2011, Chicago, Il., USA
EditorsB. Mobasher, R. Burke
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
ISBN (Print)978-1-4503-0689-6
Publication statusPublished - 2011
Event5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, United States
Duration: 23 Oct 201127 Oct 2011
Conference number: 5


Conference5th ACM Conference on Recommender Systems (RecSys 2011)
Abbreviated titleRecSys 2011
Country/TerritoryUnited States
Internet address


Dive into the research topics of 'Each to his own: how different users call for different interaction methods in recommender systems'. Together they form a unique fingerprint.

Cite this