Year: 2023
Type: article
Abstract: Numerous approaches have been developed to group learners’ behavior in an online/blended learning environment. However, most clustering analyses in this particular field only consider numeric features despite the existence of categoric features that are found important in other studies. In this study, we compare K-Means and K-Prototypes algorithms to cluster learners’ behavior in a flipped classroom implementation. From the model selection, we found that the model produced by the K-Prototypes algorithm — which included categoric features — is a better one. The statistical analysis of the clustering results of the selected K-Prototypes model shows significant differences in most of the inter-cluster comparisons, implying a good separation of the data. More importantly, we can identify the behavior in each cluster which then can be used to help learners in achieving better results in learning.
Institution: Sam Ratulangi University
Language: English
Subfield: Computer Science Applications
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: diamond
OpenAlex ID: W4324089115
