Identifying Students at Risk of Academic Failure Within the Educational Data Mining Framework.

Autor/inn/en	Sarra, Annalina; Fontanella, Lara; Di Zio, Simone
Titel	Identifying Students at Risk of Academic Failure Within the Educational Data Mining Framework. Gefälligkeitsübersetzung: Identifikation von Studenten mit dem Risiko des Studienabbruchs durch die Gewinnung von Bildungsdaten.
Quelle	In: Social indicators research, 146 (2019) 1/2, S. 41-60 PDF als Volltext Link als defekt meldenVerfügbarkeit
Sprache	englisch
Dokumenttyp	online; gedruckt; Zeitschriftenaufsatz
ISSN	0303-8300; 1573-0921
DOI	10.1007/s11205-018-1901-8
Schlagwörter	Resilienz; Datengewinnung; Determinante; Hochschulbildung; Studium; Studienerfolg; Studienmotivation; Abbruch; Risikoabschätzung; Typologie; Student; Italien
Abstract	Data mining is widely considered a powerful instrument for searching and acquiring essential relationships among different variables/attributes in a database. Data mining applied in the educational framework is referred to as educational data mining (EDM). EDM enables to get insights into various higher education phenomena, such as students' academic paths, learning behaviours and determinants of academic success or dropout. In this paper, we aim at evaluating the usefulness of a particular latent class model, the Bayesian Profile Regression, for the identification of students more likely to drop out. Considering students' performance, motivation and resilience, this technique allows to draw the profiles of students with a higher risk of academic failure. The working example is based on real data collected through an online questionnaire filled in by undergraduate students of an Italian University. (Author's Abstract, IAB-Doku).
Erfasst von	Institut für Arbeitsmarkt- und Berufsforschung, Nürnberg
Update	2020/3