Abstract
Massive Open Online Courses (MOOCs) have become an option for convenient access to education opportunities. However, the low completion rates remain a major challenge for MOOC teachers and providers. Meanwhile, very little has been known about learner experience in MOOC on Information Theory; which is a fundamental field of interest in engineering. This work-inprogress aims at promoting student completion rate in a MOOC on Information Theory by identifying effective strategies for individualized MOOC learning. In particular, the research-to-practice study takes place in a MOOC designed and taught by the third author. We established a learning experience model by extended an existing framework in the MOOC literature. We validated our model with empirical learning data collected from our own MOOC. We identified variables that predict student learning outcomes and completion. Our model enables us to further develop an Individualized Learning Path System that generates and selects the most suitable learning path for individual students.