Home

"Let's audit Learning Analytics" (LaLA) is a Moodle plugin to enable administrators and auditors of Moodle Learning Analytics models to retrieve evidence for their audit, like the sample data collected on the Moodle instance, the calculated features and predictions made by the model.

Machine learning models have often been found to be unfair, for example, when they produce more errors for certain groups¹. To ensure that unfair models are not deployed in Moodle Learning Analytics (LA) and to guarantee the trustworthiness of the deployed models, it is crucial to audit their fairness before deployment. However, Moodle currently lacks the necessary auditability features, specifically, it does not store and make available evidence that can be used to prove or disprove fairness claims. To address this lack of evidence, we developed a plugin that allows developers and administrators to train and test an LA model configuration while also storing the intermediate results and providing these data sets as downloads. By enabling fairer LA models and increasing trust in their predictions, we hope to reach more learners and maximize the potential benefits of these models.

Documentation

• Moodle Learning Analytics: What is Moodle Learning Analytics and where can I find more information?
• Auditing: What is an audit, how do I conduct an audit of a Learning Analytics system, and how can LaLA help me with that?
• Quick Start: How do I use LaLA?
• Evidence: What evidence can I retrieve through this plugin and what is it supposed to look like?
• Privacy: What measures have been taken to anonymize data and protect students' privacy?
• Security: What measures have been taken to secure access to the LaLA?
• Architecture: What is the architecture of this plugin, and how does it integrate with Moodle Learning Analytics?
• GitHub Issues: What are issues and limitations of the current release and where is the development of this plugin headed?

---

^{1. Riazy, S. and Simbeck, K. (2019) Predictive Algorithms in Learning Analytics and their Fairness. Gesellschaft für Informatik e.V. Available at: https://doi.org/10.18420/delfi2019_305. ↩}