Creating profiles of students from their interactions on the online education platform

Online education platforms have different profiles of students according to the way they use the system; some profiles contribute to the orientation of students. The aim of this thesis is to accurately predict these profiles early on and provide personalized support and guidance to students. Since this issue is very important in the development of children, clusters were created with the help of machine learning from the system interactions of children on the educational platforms used by their students. Different clusters were created for each class from 82,189 student movements taken from a special online education platform. When the clusters were analyzed, 10 different profiles were extracted. Python was used as the software language.