Computational modeling approaches help guide early design efforts for usability

Abstract

In this paper, we describe the innovative approach of using formal computational models to guide design efforts and evaluate software interfaces for usability. Decades of work in the field of HCI looked to using task analyses, live user testing and GOMS modeling techniques to help design for usability. While these methods proved helpful, guidance came after the fact. Only after the prototype interface had been designed were the traditional techniques useful in evaluating the interface. This research seeks to be innovative in two ways. First, it seeks to examine techniques that can directly impact design at the very first stages where it is most critical. Second, it demonstrates the utility of a not so often used approach, that of using formal computational models to impact design. In this research, formal computational models were used to map sequences of operations of an activity or task. A candidate interface was then designed around the formal model's recommendations for what would be most facilitative for this activity. The result was an interface that performed optimally per model predictions. Additionally, live user testing was employed and empirical observations verified and reinforced the model predictions.