A Methodology for Task-Driven Guidance Design

Abstract

Mixed-initiative Visual Analytics (VA) systems are becoming increasingly important; however, the design of such systems still needs to be formulated. We present a methodology to aid and structure the design of mixed-initiative VA systems consisting of four steps: (1) defining the target of analysis, (2) identifying the user search tasks, (3) describing the system guidance tasks, and (4) specifying which and when guidance is provided. In summary, it specifies a space of possible user tasks and then maps it to the corresponding space of guidance tasks, using recent VA task typologies for guidance and visualizations. We illustrate these steps through a case study in a real-world model-building task involving decision-making with unevenly-spaced time-oriented data. Our methodology is particularly beneficial for enriching existing VA systems with guidance, being its output a structured description of a complex guidance task schema.