Identifying potential cheaters by tracking their behaviors through mouse activities

Academic cheating is a significantly common occurrence at the university level in developing countries particularly, in Afghanistan. In online education practices, it could be a difficult task for a better process of secret reconstruction and identifying/ detecting the potential cheaters. Due to a huge number of students and the rapid increase of online education and penetration of the internet (the diversity of electronic devices used by learners in online activities), a big gap exists across creating an honest culture and teacher practices in the classroom. As such, raising the way of early prediction of potential cheaters through the mouse-tracking technique should be an urgent priority. In this paper, the authors examine the developed mouse tracking application along with the developed Moodle plugin in a blended course mid-term (20%) examination for the purpose of detecting and identifying the potential cheaters. The proposed model correctly predicted 94% of students committing illicit actions during the online mid-term examination, which can be possible to early intervene and prevent illegal actions. The study outcome can be used to analyze the learners' mouse tracking behaviors that lead to a better process of secret reconstruction and transparent space.