There is a long history of research efforts aimed at understanding the relationship between homework activity and academic achievement. While some self-report inventories involving homework activity have been useful for predicting academic performance, self-reported measures may be limited or even problematic. Here, we employ a novel method for accurately measuring students' homework activity using smartpen technology. Three cohorts of engineering students in an undergraduate statics course used smartpens to complete their homework problems, thus producing records of their work in the form of timestamped digitized pen strokes. Consistent with the time-on-task hypothesis, there was a strong and consistent positive correlation between course grade and time doing homework as measured by smartpen technology (r ϭ .44), but not between course grade and self-reported time doing homework (r ϭ Ϫ.16). Consistent with an updated version of the time-on-task hypothesis, there was a strong correlation between measures of the quality of time spent on homework problems (such as the proportion of ink produced for homework within 24 hr of the deadline) and course grade (r ϭ Ϫ.32), and between writing activity (such as the total number of pen strokes on homework) and course grade (r ϭ .49). Overall, smartpen technology allowed a fine-grained test of the idea that productive use of homework time is related to course grade.

Stahovich joined the Mechanical Engineering Department at UC Riverside in 2003 where he is currently a Professor and Chair. His research interests include pen-based computing, educational technology, design automation, and design rationale management.

No abstract

Stahovich joined the Mechanical Engineering Department at UC Riverside in 2003 where he is currently a Professor and Chair. His research interests include pen-based computing, educational technology, design automation, and design rationale management.

We present a two-step technique for learning reusable design procedures from observations of a designer in action. This technique is intended for the domain of parametric design problems in which the designer iteratively adjusts the parameters of a design so as to satisfy the design requirements. In the first step of the two-step learning process, decision tree learning is used to infer rules that predict which design parameter the designer is likely to change for any particular state of an evolving design. In the second step, decision tree learning is again used, but this time to learn explicit termination conditions for the rules learned in the first step. The termination conditions are used to predict how large of a parameter change should be made when a rule is applied. The learned rules and termination conditions can be used to automatically solve new design problems with a minimum of human intervention. Experiments with this technique suggest that it can reproduce the decision making process observed from the designer, and it is considerably more efficient than the previous technique, which was incapable of learning explicit rule termination conditions. In particular, the rule termination conditions allow the new program to automatically solve design problems with far fewer iterations than previously required.