Abstract
Massive Open Online Course (MOOC) platforms incorporate large course catalogs from which individual students may register multiple courses. We performed a network-based analysis of student achievement, considering how course-course interactions may positively or negatively affect student success. Our data set included 378,000 users and 1,000,000 unique registration events in France Université Numérique (FUN), a national MOOC platform. We adapt reliability theory to model certificate completion rates with a Weibull survival function, following the intuition that students "survive" in a course for a certain time before stochastically dropping out. Course-course interactions are found to be well described by a single parameter for user engagement that can be estimated from a user's registration profile. User engagement, in turn, correlates with certificate rates in all courses regardless of specific content. The reliability approach is shown to capture several certificate rate patterns that are overlooked by conventional regression models. User engagement emerges as a natural metric for tracking student progress across demographics and over time.
Highlights
In recent years millions of students have registered for thousands of newly created online courses with topics spanning the range of human knowledge [1]
Massive Open Online Courses (MOOCs) are a subset of online courses defined by a commitment to open access and unlimited registration [2]
The privacy policy and terms and conditions of use for the France Universite Numerique are available on the platform website
Summary
In recent years millions of students have registered for thousands of newly created online courses with topics spanning the range of human knowledge [1]. Massive Open Online Courses (MOOCs) are a subset of online courses defined by a commitment to open access and unlimited registration [2]. MOOC use is increasingly mediated though MOOC platforms, websites that offer centralized access to many courses through a standard user interface. Previous work has identified course-specific features of style and content that characterize highly effective MOOCs [3,4,5,6]. Other studies look outside the course for student-specific demographic and social factors that affect performance [7,8,9]. We consider the interaction-specific factors that come into play when users register for multiple courses. The central organization of MOOC platforms encourages multiple registrations, there has not yet been a systematic study -course effects
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
