Behavioral Performance Evaluation and Emotion Analytics of a MOOC Course via Fuzzy Modeling

Abstract

The main objective of this study is to compare and distinguish both behavioral differences and emotional changes of a group of students who "earned a certificate" after the end of a MOOC (Massive Open Online Course), versus another groups of students who "dropped out" the course unsuccessfully. To do this, a process mining process discovery technique so-called Fuzzy Miner, based on Frequency-Based and Time-Performance metrics, was applied on a set of event logs previously collected from an authentic learning environment. The resulting fuzzy graphs/models showed a significant dissimilarity between the two groups in terms of the behavioral structure and the sequence of the performed/executed tasks (and activities), the average (mean) duration of the waiting times (or inactive interval/time gaps) in addition to the emotional mood shifts and changes. The findings of the study can be beneficial to not only the MOOC course developers, but to lecturers and researchers as well, in such a way leading to higher attrition rate running online courses and syllabuses.