Sandra Michelet

Experimentation and results for calibrating automatic diagnosis belief linked to problem solving modalities: a case study in electricity

Learners increasingly work with virtual laboratories that provide various activities and tools, including sophisticated modeling and simulation systems. The learning environments have to combine traces to establish the most precise diagnosis possible on the learners activity. This paper presents a diagnosis tool, called DiagElec, establishing a diagnosis on the learners activity. DiagElec integrates a notion of belief, which is related to the modalities in the generated diagnoses. To analyze our model, we have carried out a two-phase experiment, first with learners and then with teachers. From the corpus of diagnosis done by the teachers, we are looking for the emergence of a model of human behavior to recalibrate the degree of belief defined into the diagnosis rules.

Setting up On-Line Learning Experiments: The LearningLab Platform

To carry out experiments into classrooms, in order to test hypothesis or new learning tools needs to perform recurrent complex and time-consuming tasks. We propose means for setting up Web based experiments by distinguishing the experimentation perspective and the learning perspective.This paper presents the experimentation platform we have developed for the kaleidoscope network of excellence (NoE) ldquoshared virtual laboratoryrdquo action. This platform, called ldquoLearningLabrdquo, gives a concrete expression of our proposal, and provides researchers with useful tools for each phase of an experiment. The usability of this platform has been put to the test with two experimentations about electricity learning.