PROJECT TITLE :

Voyager: Exploratory Analysis via Faceted Browsing of Visualization Recommendations

ABSTRACT:

General visualization tools usually need manual specification of views: analysts must choose information variables and then choose that transformations and visual encodings to use. These decisions often involve each domain and visualization style expertise, and may impose a tedious specification method that impedes exploration. In this paper, we seek to enrich manual chart construction with interactive navigation of a gallery of automatically-generated visualizations. We have a tendency to contribute Voyager, a mixed-initiative system that supports faceted browsing of suggested charts chosen in keeping with statistical and perceptual measures. We tend to describe Voyager's architecture, motivating design principles, and strategies for generating and interacting with visualization recommendations. In a study comparing Voyager to a manual visualization specification tool, we tend to notice that Voyager facilitates exploration of previously unseen data and ends up in increased data variable coverage. We tend to then distill design implications for visualization tools, in particular the necessity to balance speedy exploration and targeted question-answering.