When (ish) is My Bus?: User-centered Visualizations of Uncertainty in Everyday, Mobile Predictive Systems

By Matthew Kay, Tara Kola, Jessica R. Hullman, Sean A Munson. International Conference on Human Factors in Computing Systems, 2016

304 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Transportation

View Paper: https://www.semanticscholar.org/paper/e75957f41a092a1a7b436375b949d205972d3474

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 Transportation

Adrian Weller

Citations in the corpus

Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda (2018, background): “Research explored the need for [111] and provision of explanations in physical space, such as smart environments [177, 178, 179], the office [26], smart homes [18, 30, 131, 183] and on the move [90, 116].”
AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap (2023, background): “For example, a line of HCI research explored more user-friendly visualization designs to overcome the trouble that people often have understanding statistical uncertainty and the cognitive biases they bring (Fernandes et al., 2018; Kay et al., 2016).”
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems (2018, background): “users’ mental models to determine user understanding of intelligent systems in various applications. For example, Costanza et al. [23] studied how users understand a smart grid system, and Kay et al. [56] studied how users understand and adapt to uncertainty in machine learning prediction of a bus a”
Will You Accept an Imperfect AI?: Exploring Designs for Adjusting End-user Expectations of AI Systems (2019, background): “While presence of visualization has been found beneficial, past work has also indicated that too complex visualizations (e.g., probability distributions) are too difficult for the everyday user to interpret [24, 26].”
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty (2020, background): “[64] develop quantile dot plots to convey distributions (see Figure 3b for an example).”