Systematic Yet Flexible Discovery: Guiding Domain Experts Through Exploratory Data Analysis
Ben Shneiderman
Abstract
During exploratory data analysis, visualizations are often useful for making
sense of complex data sets. However, as data sets increase in size and
complexity, static information visualizations decrease in comprehensibility.
Interactive techniques can yield valuable discoveries, but current data analysis
tools typically support only opportunistic exploration that may be inefficient
and incomplete. We present a refined architecture that uses systematic yet
flexible (SYF) design goals to guide domain expert users through complex
exploration of data over days, weeks and months. The SYF system aims to support
exploratory data analysis with some of the simplicity of an e-commerce check-out
while providing added flexibility to pursue insights. The SYF system provides an
overview of the analysis process, suggests unexplored states, allows users to
annotate useful states, supports collaboration, and enables reuse of successful
strategies. The affordances of the SYF system are demonstrated by integrating it
into a social network analysis tool employed by social scientists and
intelligence analysts. The SYF system is a tool-independent component and can be
incorporated into other data analysis tools.