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

Authors:
Bart P. Knijnenburg;Niels J.M. Reijmer;Martijn C. Willemsen
Affiliations:
University of California, Irvine, Irvine, CA, USA;Eindhoven University of Technology, Eindhoven, Netherlands;Eindhoven University of Technology, Eindhoven, Netherlands
Venue:
Proceedings of the fifth ACM conference on Recommender systems
Year:
2011

Citing 16
Cited 7

On the recommending of citations for research papers

CSCW '02 Proceedings of the 2002 ACM conference on Computer supported cooperative work
Motivating Human–Agent Interaction: Transferring Insights from Behavioral Marketing to Interface Design

Electronic Commerce Research
Persuasive Technology: Using Computers to Change What We Think and Do

Persuasive Technology: Using Computers to Change What We Think and Do
Adaptive interfaces and agents

The human-computer interaction handbook
Personalizing to Product Category Knowledge: Exploring the Mediating Effect of Shopping Tools on Decision Confidence

HICSS '04 Proceedings of the Proceedings of the 37th Annual Hawaii International Conference on System Sciences (HICSS'04) - Track 7 - Volume 7
Reactance to Recommendations: When Unsolicited Advice Yields Contrary Responses

Marketing Science
Evaluating product search and recommender systems for E-commerce environments

Electronic Commerce Research
Recommendation Agents for Electronic Commerce: Effects of Explanation Facilities on Trusting Beliefs

Journal of Management Information Systems
Research Note: User Design of Customized Products

Marketing Science
How Users Perceive and Appraise Personalized Recommendations

UMAP '09 Proceedings of the 17th International Conference on User Modeling, Adaptation, and Personalization: formerly UM and AH
Understanding the effect of adaptive preference elicitation methods on user satisfaction of a recommender system

Proceedings of the third ACM conference on Recommender systems
The effect of preference elicitation methods on the user experience of a recommender system

CHI '10 Extended Abstracts on Human Factors in Computing Systems
Interfaces for eliciting new user preferences in recommender systems

UM'03 Proceedings of the 9th international conference on User modeling
The effects of personalizaion and familiarity on trust and adoption of recommendation agents

MIS Quarterly
E-commerce product recommendation agents: use, characteristics, and impact

MIS Quarterly
Explaining the user experience of recommender systems

User Modeling and User-Adapted Interaction

Explaining the user experience of recommender systems

User Modeling and User-Adapted Interaction
Conducting user experiments in recommender systems

Proceedings of the sixth ACM conference on Recommender systems
Inspectability and control in social recommenders

Proceedings of the sixth ACM conference on Recommender systems
Beyond lists: studying the effect of different recommendation visualizations

Proceedings of the sixth ACM conference on Recommender systems
Visualizing recommendations to support exploration, transparency and controllability

Proceedings of the 2013 international conference on Intelligent user interfaces
A field study of a visual controllable talk recommender

Proceedings of the 2013 Chilean Conference on Human - Computer Interaction
See what you want to see: visual user-driven approach for hybrid recommendation

Proceedings of the 19th international conference on Intelligent User Interfaces

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.