We describe our approach to the computation and visual representation of the learning dynamics of a Massive Open Online Course (MOOC), where the educational strategy of Peer Assessment is used. The state of the MOOC, at a point in time, is representable through the student models and the relationships and data produced during the Peer Assessment. Such representation is rendered through a Graph Embedding approach, supported by Principal Component Analysis, as a point in a 2-dimensional space. The evolution of the MOOC, during a series of Peer Assessment sessions, is then representable as the path of the points where the MOOC status has been. Basing on a simulated MOOC, with 1000 students, modeled by a normal distribution of the student model features, we show that the proposed representation can picture effectively the evolution of the MOOC in time.
Dettaglio pubblicazione
2021, Lecture Notes in Networks and Systems, Pages 114-123 (volume: 326)
Deep Learning to Monitor Massive Open Online Courses Dynamics (04b Atto di convegno in volume)
Botticelli M., Gasparetti F., Sciarrone F., Temperini M.
ISBN: 978-3-030-86617-4; 978-3-030-86618-1
Gruppo di ricerca: Human-Computer Interaction