This article describes an example of data mining techniques applied to an open educational environment. These novel assessment methods in the educational robotics (ER) field provide empirical evidence of problem-solving styles behind the key tasks of proposed activities within real operative scenarios. A supervised, mixed machine learning (ML) approach was applied to data from seven Italian secondary schools (197 students), and four ML techniques [logistic regression (LR), support vector machine (SVM), k-nearest neighbors (KNN), and random forest (RF)] were explored to predict students' success.
Identification and Assessment of Educational Experiences: Utilizing Data Mining with Robotics / Scaradozzi, D.; Cesaretti, L.; Screpanti, L.; Mangina, E.. - In: IEEE ROBOTICS AND AUTOMATION MAGAZINE. - ISSN 1070-9932. - 28:4(2021), pp. 103-113. [10.1109/MRA.2021.3108942]
Identification and Assessment of Educational Experiences: Utilizing Data Mining with Robotics
Scaradozzi D.
;Cesaretti L.;Screpanti L.;
2021-01-01
Abstract
This article describes an example of data mining techniques applied to an open educational environment. These novel assessment methods in the educational robotics (ER) field provide empirical evidence of problem-solving styles behind the key tasks of proposed activities within real operative scenarios. A supervised, mixed machine learning (ML) approach was applied to data from seven Italian secondary schools (197 students), and four ML techniques [logistic regression (LR), support vector machine (SVM), k-nearest neighbors (KNN), and random forest (RF)] were explored to predict students' success.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
