Workload Analytics
Modelling workloads to help students plan their term/program and administration to manage their course /program design.
Workload Analytics, a proof of concept developed by D2L Labs, explores how to model workload intensity (as a proxy for the stress that a user feels) and identify peak periods that need to be managed.
Individual learners can use the data to better select courses or training while maintaining a balanced workload. Learning/training providers can use the data when developing courses or programs to better account for peak periods that may negatively impact learner success.
Key Ideas:
- Differentiated intensity models: Different types of projects and assignments have varied impacts on the user. For example, the intensity of a high stakes assessment, such as a final exam, has a different impact than a low stakes assessment, such as a weekly quiz or assignment. The system differentiates between these types of assessments.
- Big picture view: A dashboard view that displays a summary across a learner’s workload to help them understand when they will need to be more mindful of time management. For learning/training providers the dashboard provides a summary of the cumulative workload across learners to help them design programs that better support successful outcomes.
- Optimize workloads: Remove workload hotspots by changing the structure and timing of assessments to create a more balanced workload for learners.

Technologies
Machine Learning, Artificial Intelligence

Status
Proof of Concept
You can unsubscribe at any time. Personal information may be collected, used and disclosed in accordance with our privacy policy. Please note that if you do not provide express consent, we may, in limited circumstances, continue to provide communications to you under implied consent provisions of applicable anti-spam legislation.