No abstract

No abstract

Interest in studying Massive Online Open Courses (MOOC) learners’ sessions has grown as a result of the retention and completion issues that these courses present. Applying process mining to study this phenomenon is difficult due to the freedom of navigation that these courses give their students. The goal of this research is to provide a domain-driven top-down method that enables educators who are unfamiliar with data and process analytics to search for a set of preset high-level concepts in their own MOOC data, hence simplifying the use of typical process mining techniques. This is accomplished by defining a three-stage process that generates a low-level event log from a minimum data model and then abstracts it to a high-level event log with seven possible learning dynamics that a student may perform in a session. By examining the actions of students who successfully completed a Coursera introductory programming course, the framework was tested. As a consequence, patterns in the repetition of content and assessments were described; it was discovered that students’ willingness to evaluate themselves increases as they advance through the course; and four distinct session types were characterized via clustering. This study shows the potential of employing event abstraction strategies to gain relevant insights from educational data.

In conjunction with the rapid expansion of Massive Open Online Courses (MOOCs), academic interest has grown in the analysis of MOOC student study sessions. Education researchers have increasingly regarded process mining as a promising tool with which to answer simple questions, including the order in which resources are completed. However, its application to more complex questions about learning dynamics remains a challenge. For example, do MOOC students genuinely study from a resource or merely skim content to understand what will come next? One common practice is to use the resources directly as activities, resulting in spaghetti process models that subsequently undergo filtering. However, this leads to over-simplified and difficult-to-interpret conclusions. Consequently, an event abstraction becomes necessary, whereby low-level events are combined with high-level activities. A wide range of event abstraction techniques has been presented in process mining literature, primarily in relation to data-driven bottom-up strategies, where patterns are discovered from the data and later mapped to education concepts. Accordingly, this paper proposes a domain-driven top-down framework that allows educators who are less familiar with data and process analytics to more easily search for a set of predefined high-level concepts from their own MOOC data. The framework outlined herein has been successfully tested in a Coursera MOOC, with the objective of understanding the in-session behavioral dynamics of learners who successfully complete their respective courses.