FluidViews: Adaptive Drag-and-Drop Token Filters for Heterogeneous Multi-View Visual Analytics

Abstract

Interactive visual analytics workflows are often disrupted by rigid filter panels and context switches that break analysts' cognitive flow. We introduce FluidViews, a web-based framework that elevates filters to first-class, manipulable objects through two novel direct-manipulation interactions. Copy-as-Highlight enables users to duplicate any visual mark into a persistent highlight token for rapid, transient cross-view comparison, while Drag-as-Filter allows analysts to pick up a mark and drop it onto another view to apply context-sensitive filters in place no menus, panels, or modal dialogs required. An optional pop-out micro-view provides on-demand, spatially independent subviews for detailed inspection without disrupting the primary workspace. By embedding these lightweight gestures into coordinated multi-view environments, FluidViews preserves analytic momentum, reduces cognitive overhead, and supports fluid, multi-step exploration across heterogeneous datasets. We describe the system's design and implementation, illustrate its application in exploratory workflows, and discuss how tangible filter objects can transform interactive data exploration.