Eberly Center

Relationship between consistency of student behavior and their performance in an online course

Sakr, M., Zhang, H., Dashti, C. & M. An

In this work we explore the relationship between student behavior and their performance in a project-based online cloud computing course. Log data from 154 students were collected from the project portal (The Project Zone), the auto-grading system, and the cloud-service provider AWS. Using the logs we observe when students work on a project, how often they submit solutions to our auto-graders and when they provision cloud resources. Using these metrics we estimate student time-on-task for each project and analyze behavior in terms of time-on-task, number of submissions and cost of cloud resources. We measure the consistency of student behavior by the variance of their behavior percentile across eleven projects. Correlation is not generally found between behavior and performance. However, high performing students show significantly greater consistency in behavior in all dimensions considered. In future work, we plan to further investigate student behavior consistency and possible causal relationships with performance and learning.

Majd Sakr, Language Technologies Institute SCS

Hongyi Zhang, Computer Science Department SCS

Cameron Dashti, Computer Science Department SCS

Marshall An, Computer Science Department SCS