Bayesian Modelling of Alluvial Diagram Complexity

TL;DR

This paper investigates how visual features of alluvial diagrams affect user interpretation and perceived complexity, using Bayesian models to predict task performance and subjective assessments based on diagram complexity.

Contribution

It introduces a Bayesian modeling approach to predict how different visual features influence perceived and task-related complexity in alluvial diagrams.

Findings

Multiple visual features impact diagram complexity

Feature importance varies between task complexity and perceived complexity

Bayesian models can predict user classification of diagram complexity

Abstract

Alluvial diagrams are a popular technique for visualizing flow and relational data. However, successfully reading and interpreting the data shown in an alluvial diagram is likely influenced by factors such as data volume, complexity, and chart layout. To understand how alluvial diagram consumption is impacted by its visual features, we conduct two crowdsourced user studies with a set of alluvial diagrams of varying complexity, and examine (i) participant performance on analysis tasks, and (ii) the perceived complexity of the charts. Using the study results, we employ Bayesian modelling to predict participant classification of diagram complexity. We find that, while multiple visual features are important in contributing to alluvial diagram complexity, interestingly the importance of features seems to depend on the type of complexity being modeled, i.e. task complexity vs. perceived complexity.