hrcak mascot   Srce   HID

Croatian Operational Research Review, Vol. 6 No. 1, 2015.

Izvorni znanstveni članak
https://doi.org/10.17535/crorr.2015.0009

Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model

Ivana Đurđević Babić ; Faculty of Education, Josip Juraj Strossmayer University of Osijek, Osijek, Croatia

Puni tekst: engleski, pdf (263 KB) str. 105-120 preuzimanja: 597* citiraj
APA 6th Edition
Đurđević Babić, I. (2015). Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model. Croatian Operational Research Review, 6 (1), 105-120. https://doi.org/10.17535/crorr.2015.0009
MLA 8th Edition
Đurđević Babić, Ivana. "Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model." Croatian Operational Research Review, vol. 6, br. 1, 2015, str. 105-120. https://doi.org/10.17535/crorr.2015.0009. Citirano 21.01.2019.
Chicago 17th Edition
Đurđević Babić, Ivana. "Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model." Croatian Operational Research Review 6, br. 1 (2015): 105-120. https://doi.org/10.17535/crorr.2015.0009
Harvard
Đurđević Babić, I. (2015). 'Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model', Croatian Operational Research Review, 6(1), str. 105-120. doi: https://doi.org/10.17535/crorr.2015.0009
Vancouver
Đurđević Babić I. Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model. Croatian Operational Research Review [Internet]. 2015 [pristupljeno 21.01.2019.];6(1):105-120. doi: https://doi.org/10.17535/crorr.2015.0009
IEEE
I. Đurđević Babić, "Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model", Croatian Operational Research Review, vol.6, br. 1, str. 105-120, 2015. [Online]. doi: https://doi.org/10.17535/crorr.2015.0009

Sažetak
Student satisfaction with courses in academic institutions is an important issue and is recognized as a form of support in ensuring effective and quality education, as well as enhancing student course experience. This paper investigates whether there is a connection between student satisfaction with courses and log data on student courses in a virtual learning environment. Furthermore, it explores whether a successful classification model for predicting student satisfaction with course can be developed based on course log data and compares the results obtained from implemented methods. The research was conducted at the Faculty of Education in Osijek and included analysis of log data and course satisfaction on a sample of third and fourth year students. Multilayer Perceptron (MLP) with different activation functions and Radial Basis Function (RBF) neural networks as well as classification tree models were developed, trained and tested in order to classify students into one of two categories of course satisfaction. Type I and type II errors, and input variable importance were used for model comparison and classification accuracy.
The results indicate that a successful classification model using tested methods can be created. The MLP model provides the highest average classification accuracy and the lowest preference in misclassification of students with a low level of course satisfaction, although a t-test for the difference in proportions showed that the difference in performance between the compared models is not statistically significant. Student involvement in forum discussions is recognized as a valuable predictor of student satisfaction with courses in all observed models.

Ključne riječi
classification; neural networks; classification tree; course satisfaction; log data

Hrčak ID: 138589

URI
https://hrcak.srce.hr/138589

Posjeta: 817 *