Seminar from Rémi Venant, Lecturer at LIUM, team TEL
Are learning analytics doomed to failure?
learning analytics (LA) are undergoing increasing development, and following the COVID-19 pandemic and the forced introduction of large-scale distance learning, it is reasonable to anticipate an acceleration in the introduction of hybrid practices and therefore a growing need for LA. However, due to an increase in their intrinsic complexity, particularly through the use of increasingly advanced statistical models and artificial intelligence (AI) techniques, they are struggling to be put into production in a real learning context. Improving the explainability of AIs for non expert users in data analysis is therefore a crucial issue for Technology Enhanced Learning.
This presentation aims to detail this issue through the exposition of different works currently being carried out within the TEL team of the LIUM which, although different, are all facing this issue. The subsequent engagement in a joint discussion with the LST team would allow the mutual sharing of experience and knowledge on AI techniques applied in different fields, in order to offer a new perspective and eventually identify new approaches to the problem of the explainability of LAs.