An Automated Stable Personalised Partner Selection for Collaborative Privacy Education

Abstract

E-learning platforms have never been as in-demand as they are now since the recent pandemic making privacy education more important than ever. However, for the most part, these platforms are single-user learning environments and lack student-student interactions. To overcome this deficiency, we propose a collaborative e-learning platform for privacy education that matches students in a stable and automatic manner according to students’ preferences. Each student is represented by a vector profile that is created from behavioural skills and academic knowledge obtained from the platform. Once the preferences are determined, the residents-hospitals matching algorithm is applied to select students who will collaborate with one another. Experimental results show that the proposed model offers an effective way to create stable, thus satisfied, coalitions of students from two groups of arbitrary sizes. In addition, the automation allows students to skip the tedious process of manually selecting partners. Therefore, saving their time to collaborate on privacy education with their teammates helping them to increase their privacy awareness.