Explaining cognitive breakpoints to chunk visual analytic actions for transparency in sensemaking

Sensemaking is inherently a fluid activity involving transitions between mental and interaction states but may create a gap between them due to lack of accuracy and precision into adopted visualization techniques. We have found through this research that detection and explanation of those transition points can bridge that gap and maintain transparency in sensemaking visual analytic activities. We have defined those transition points as ‘Breakpoints’ and developed machine learning models to contextualize streams of analytic actions for inferring those at micro analytic level. We also have presented visual explanations by unfolding black box calculations for transparent validation of all machine produced results in terms of reliability, accuracy and relevance.

Special Issue on Human-Centered Visualization Approaches to AI Explainability, Interpretability, Understanding, and Ethics