Designing Bias Mitigation Interventions
In this work, we explore the ways in which the design of visualizations may be used to mitigate cognitive biases. We derive a design space comprised of 8 dimensions that can be manipulated to impact a user’s cognitive and analytic processes and describe them through an example hiring scenario. This design space can be used to guide and inform future vis systems that may integrate cognitive processes more closely.
Computationally Characterizing Human Bias in Vis
In this paper, we establish a conceptual framework for considering bias assessment through human-in-the-loop systems and lay the theoretical foundations for bias measurement. We propose six preliminary metrics to systematically detect and quantify bias from user interactions and demonstrate how the metrics might be implemented in an existing visual analytic system, InterAxis.
Value of Visualization
In this work, we create a heuristic-based evaluation methodology to accompany the value equation for assessing interactive visualizations. We refer to the methodology colloquially as ICE-T, based on an anagram of the four value components. Our approach breaks the four components down into guidelines, each of which is made up of a small set of low-level heuristics. Evaluators who have knowledge of visualization design principles then assess the visualization with respect to the heuristics.
Teaching Machine Teachers
Machine Teaching (MT) is an emerging practice where people, without Machine Learning (ML) expertise, provide rich information beyond labels in order to create ML models. In this paper, we explore and show how end-users without MT experience successfully build ML models using the MT process, and achieve results not far behind those of MT experts.