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.
Deep Learning to Monitor Massive Open Online Courses Dynamics / Botticelli, M.; Gasparetti, F.; Sciarrone, F.; Temperini, M.. - 326:(2022), pp. 114-123. (Intervento presentato al convegno International Conference on Methodologies and Intelligent Systems for Technology Enhanced Learning tenutosi a Salamanca; Spain) [10.1007/978-3-030-86618-1_12].
Deep Learning to Monitor Massive Open Online Courses Dynamics
Botticelli M.
;Sciarrone F.
;Temperini M.
2022
Abstract
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.File | Dimensione | Formato | |
---|---|---|---|
Botticelli_Deep_2022.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.16 MB
Formato
Adobe PDF
|
1.16 MB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.