Process modeling and decision mining in a collaborative distance learning environment

This paper is divided into four main parts. In the first part of the study, we identified the most significant factors that affect the performance of groups in collaborative learning situations. The results showed that the extent of communication, interactions and involvement/participation between students have crucial impacts on the performance of groups. In the second part of the study, we defined and explained specific alphabets and keywords derived from a collected event log during a distance learning activity using a real-time multi-user concept mapping service. Our aim was to interpret the data in such a way that eventually can increase the instructor's awareness about entire the collaborative process. In the third part of the study, we used several statistical and process mining techniques in order to discover and compare distinguished patterns of interaction and involvement between the groups with high and low performance. The results showed that the extent of students' interaction was four times greater in the high performance groups. Similarly, the extent of students' involvement and participation was three times greater in the high performance groups compared with the low performance groups. In the fourth part of the study, we analyzed the extent of communication with respect to textual and semantic contributions of the students written/typed and shared in the chat rooms during the online distance activity. The results showed that the level of students' communication was two times greater in the groups with high performance. And finally, we applied a Decision Tree/Rules technique to extract a model of decisions (as well as their possible consequences) about performance of groups in collaborative learning situations.