Share This Author
Explaining the user experience of recommender systems
- Bart P. Knijnenburg, M. Willemsen, Zeno Gantner, Hakan Soncu, Chris Newell
- Computer ScienceUser Modeling and User-Adapted Interaction
- 1 October 2012
This paper proposes a framework that takes a user-centric approach to recommender system evaluation that links objective system aspects to objective user behavior through a series of perceptual and evaluative constructs (called subjective system aspects and experience, respectively).
Inspectability and control in social recommenders
- Bart P. Knijnenburg, Svetlin Bostandjiev, J. O'Donovan, A. Kobsa
- Computer ScienceRecSys '12
- 9 September 2012
An online user experiment with a Facebook music recommender system that gives users control over the recommendations is performed, and the results show that inspectability and control indeed increase users' perceived understanding of and control of the system, their rating of the recommendation quality, and their satisfaction with the system.
Each to his own: how different users call for different interaction methods in recommender systems
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-personalizedRecommender that just displays the most popular items.
Evaluating Recommender Systems with User Experiments
This chapter provides a detailed practical description of how to conduct user experiments, covering the following topics: formulating hypotheses, sampling participants, creating experimental manipulations, measuring subjective constructs with questionnaires, and statistically evaluating the results.
Privacy Aspects of Recommender Systems
- A. Friedman, Bart P. Knijnenburg, K. Vanhecke, L. Martens, S. Berkovsky
- Computer ScienceRecommender Systems Handbook
It is concluded that a considerable effort is still required to develop practical recommendation solutions that provide adequate privacy guarantees, while at the same time facilitating the delivery of high-quality recommendations to their users.
Understanding choice overload in recommender systems
- Dirk Bollen, Bart P. Knijnenburg, M. Willemsen, Mark P. Graus
- Computer ScienceRecSys '10
- 26 September 2010
Investigation of the effect of recommendation set size and set quality on perceived variety, recommendation set attractiveness, choice difficulty and satisfaction with the chosen item shows that larger sets containing only good items do not necessarily result in higher choice satisfaction compared to smaller sets.
Making Decisions about Privacy: Information Disclosure in Context-Aware Recommender Systems
A unified approach to privacy decision research is described that describes the cognitive processes involved in users’ “privacy calculus” in terms of system-related perceptions and experiences that act as mediating factors to information disclosure.
A pragmatic procedure to support the user-centric evaluation of recommender systems
This work introduces a pragmatic procedure to evaluate recommender systems for experience products with test users, within industry constraints on time and budget.
Recommender Systems for Self-Actualization
A new direction for recommender systems research is presented with the main goal of supporting users in developing, exploring, and understanding their unique personal preferences.
Inferring Capabilities of Intelligent Agents from Their External Traits
It is demonstrated that the mental model users form of an agent-based system is inherently integrated (as opposed to the compositional mental model they form of conventional interfaces): Cues provided by the system do not instill user responses in a one-to-one matter but are instead integrated into a single mental model.