Students' behavior on social media sites — A data mining approach

Abstract

Data preparation is crucial for the validity of the resulting data model and its subsequent successful application. The paper presents a preprocessing of the data on the behavior of students on social media sites using the CRISP-DM methodology. Data was collected through questioner shared among prospect students of Faculty of Economics Subotica. This has created an adequate platform for the implementation of different intelligent methods. This paper illustrates the application of clustering techniques to these data in order to identify specific profiles and patterns of student behavior on social media sites.