Applying observations of work activity in designing prototype data analysis tools

Designers, implementers, and marketers of data analysis tools typically have different perspectives than end users. Consequently, data analysts often find themselves using tools focused on graphics and programming concepts rather than concepts which reflect their own domain and the context of their work. Some user studies focus on usability tests late in development; others observe work activity, but fail to show how to apply that knowledge in design. This paper describes a methodology for applying observations of data analysis work activity in prototype tool design. The approach can be used both in designing improved data analysis tools, and customizing visualization environments to specific applications. We present an example of user-centered design for a prototype tool to cull large data sets. We revisit the typical graphical approach of animating a large data set from the point of view of an analyst who is culling data. Field evaluations using the prototype tool not only revealed valuable usability information, but initiated in-depth discussions about user's work, tools, technology, and requirements.<
>