Visual Designs for Binned Aggregation of Multi-Class Scatterplots
This work addresses visualization challenges for analysts dealing with large multi-class scatterplot data, but it is incremental as it builds on existing binning techniques.
The paper tackles the problem of visualizing large multi-class 2D point data by exploring and providing guidelines for binned aggregation designs, assessing their appropriateness for different analysis tasks and offering a web-based tool for experimentation.
Point sets in 2D with multiple classes are a common type of data. A canonical visualization design for them are scatterplots, which do not scale to large collections of points. For these larger data sets, binned aggregation (or binning) is often used to summarize the data, with many possible design alternatives for creating effective visual representations of these summaries. There are a wide range of designs to show summaries of 2D multi-class point data, each capable of supporting different analysis tasks. In this paper, we explore the space of visual designs for such data, and provide design guidelines for different analysis scenarios. To support these guidelines, we compile a set of abstract tasks and ground them in concrete examples using multiple sample datasets. We then assess designs, and survey a range of design decisions, considering their appropriateness to the tasks. In addition, we provide a web-based implementation to experiment with design choices, supporting the validation of designs based on task needs.