Article: Towards an ontology-based system for intelligent prediction of student dropouts in distance education Journal: International Journal of Management in Education (IJMIE) 2008 Vol.2 No.2 pp.172 - 194 Abstract: The objective of this work was to design an intelligent web portal to serve as a service provider for predicting which students of the Hellenic Open University (HOU) are dropout-prone students; i.e., such students indirectly generate |Student Dropout Statements| (SDSs). These statements are generated if a combination of events occurs; for example, a student is not computer literate, he/she is absent from his/her first face-to-face consulting meeting with the tutor, and/or he/she has failed in the first written assignment. The portal has been conceived to help tutors to detect dropout-prone students. The information contained in the portal is related to |Formal Students Statements| (FSSs) such as class records or the student registry of the HOU. The portal helps tutors to find students with a high probability of dropping out. For this purpose, the knowledge of the student domain has been represented by means of an ontology, which has been used to guide the design of the application and to supply the system with semantic capabilities. The reasoning engine of the system executes logic rules related with well-established student attributes, which characterise a student as dropout-prone or not. Inderscience Publishers - linking academia, business and industry through research

Title: Towards an ontology-based system for intelligent prediction of student dropouts in distance education

Authors: Dimitris Kanellopoulos, Sotiris Kotsiantis

Addresses: Educational Software Development Laboratory (ESDLab), Department of Mathematics, University of Patras, GR 265 00, Patras, Greece. ' Department of Computer Science and Technology, University of Peloponnese, GR 221 00, Tripolis, Greece

Abstract: The objective of this work was to design an intelligent web portal to serve as a service provider for predicting which students of the Hellenic Open University (HOU) are dropout-prone students; i.e., such students indirectly generate |Student Dropout Statements| (SDSs). These statements are generated if a combination of events occurs; for example, a student is not computer literate, he/she is absent from his/her first face-to-face consulting meeting with the tutor, and/or he/she has failed in the first written assignment. The portal has been conceived to help tutors to detect dropout-prone students. The information contained in the portal is related to |Formal Students Statements| (FSSs) such as class records or the student registry of the HOU. The portal helps tutors to find students with a high probability of dropping out. For this purpose, the knowledge of the student domain has been represented by means of an ontology, which has been used to guide the design of the application and to supply the system with semantic capabilities. The reasoning engine of the system executes logic rules related with well-established student attributes, which characterise a student as dropout-prone or not.

Keywords: ontology; student dropouts; student modelling; distance education; Hellenic Open University; HOU; intelligent prediction; intelligent web portals; internet; dropout prediction; semantics.

DOI: 10.1504/IJMIE.2008.018391

International Journal of Management in Education, 2008 Vol.2 No.2, pp.172 - 194

Published online: 19 May 2008 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Towards an ontology-based system for intelligent prediction of student dropouts in distance education

Keep up-to-date