Towards improving trust in context-aware systems by displaying system confidence

By Stavros Antifakos, Nicky Kern, Bernt Schiele, Adrian Schwaninger. 2005

121 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Systems, Information Systems and Management

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Information Systems

In Information Systems and Management

Citations in the corpus

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, background): “(See also Antifakos et al., 2005; Dourish, 1995; Suermondt and Cooper, 1992; Tullio et al., 2007).”
Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda (2018, background): “The fallibility of sensing and inference systems presents challenges to understanding, that can be addressed by visualizing uncertainty [7, 90, 115, 151].”
Progressive Disclosure: Designing for Effective Transparency (2018, background): “Others have shown that interventions that simply show prediction confidence improve users system perceptions [4].”
Assessing demand for intelligibility in context-aware applications (2009, methodology): “Using the open coding method of grounded theory [26], and drawing from question types employed previously [3, 20], we derived a set of information types that users are interested in for context-aware applications.”
How it works: a field study of non-technical users interacting with an intelligent system (2007, background): “showed that confidence levels could increase user trust in an intelligent notification system [1].”
Will You Accept an Imperfect AI?: Exploring Designs for Adjusting End-user Expectations of AI Systems (2019, methodology): “Prior work has compared the use of text vs. visualizations for communicating various statistical aspects of algorithms [4, 16, 43, 50].”
Trust in Automation (2015, background): “In addition to training, several studies have shown that decision aids designed to supplement their decision making with real-time confidence levels help users calibrate their trust appropriately (Antifakos, Kern, Schiele, & Schwaninger, 2005; McGuirl & Sarter, 2006).”
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems (2018, background): “Others have looked at changes to user awareness over time by displaying system confidence and uncertainty of the machine learning outputs in applications with different degrees of criticality [10, 96].”