PatternSight: A Perceptual Grouping Effectiveness Assessment Approach for Elements in Charts

The boom in visualization generation tools has significantly lowered the threshold for chart authoring. However, without a solid grasp of perceptual mechanisms, chart authors may struggle to assess the effectiveness of their designs and to select a suitable representation for conveying intended data patterns. To address this issue, we propose a perceptual grouping simulation model that can predict how chart viewers perceptually organize visual elements into element groups perceived as graphical patterns. The perceptual grouping simulation model integrates perceptual grouping principles into visual feature extraction of chart elements to provide interpretable model outcomes. Empirical evaluation with human participants demonstrated that our model can effectively learn the perceptual grouping tendencies of most viewers and accommodate a diversity of perceptual grouping outcomes. We also embed the model into a prototype interface called PatternSight to facilitate chart authors in assessing whether the chart design can satisfy their pattern representation requirements and determining feasible improvements of visual design. According to user experiment results, PatternSight can effectively assist chart authors in optimizing chart design for representing data patterns.