Inspectability and control in social recommenders

By Bart P. Knijnenburg, Svetlin Bostandjiev, John O'Donovan, Alfred Kobsa. 2012

163 citations recorded by the source corpus.

Subfields: Communication, Literature and Literary Theory, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Communication

In Literature and Literary Theory

In Statistical and Nonlinear Physics

Citations in the corpus

Enhancing Transparency and Control When Drawing Data-Driven Inferences About Individuals (2016, background): “show that inspectability and control of the system increased users’ ratings for recommendations and their satisfaction with the system.(17) A related study finds that different types of explanations by a recommendation agent enhance users’ trust in the system.”
Designing Explanation Interfaces for Transparency and Beyond (2019, methodology): “Instead of interactive recommender [7, 23], we attached an explanation icon next to each social recommendation.”
User Preferences for Hybrid Explanations (2017, background): “In addition to user preferences and design criteria for explanations, several GUIs and visualizations have been proposed for recommendations, including concentric circles (PeerChooser [11, 18]), clustermaps (TalkExplorer [29]), Venn diagrams (SetFusion [21]), and paths among columns (TasteWeights [3”
ExpLOD: A Framework for Explaining Recommendations based on the Linked Open Data Cloud (2016, background): “A similar attempt is due to [5], who demonstrated that a graph-based explanation results in a better user experience, However, they focused on the usage of graphs for visualization purposes, while our contribution exploits graphs for modeling the properties describing the items and identifying the…”
Evaluating Recommender Systems with User Experiments (2015, methodology): “In [62] we demonstrate that displaying such a “recommendation graph” increases the inspectability of the recommendations, and ultimately users’ satisfaction with the system.”
Make it personal: A social explanation system applied to group recommendations (2017, background): “Although social explanations have been included for individual recommenders (Groh et al., 2012; Sharma and Cosley, 2013; Knijnenburg et al., 2012) there is a lack of explanation methods for these social group recommendation approaches.”