Mining of Learning Interaction Patterns in MOOCs Forums

Massive Open Online Courses (MOOCs) are growing substantially in numbers, and also in interest from the educational community. MOOCs are online courses aimed at large-scale interactive participation and open access via the Web that made them possible for anyone with an internet connection to enroll in free, university level courses. In this paper, we propose a novel method to discover various types of new knowledge on forums discussions. We investigate data mining techniques to detect and analyze frequent learning discussion patterns in MOOCs forums. We investigate and characterize discussion interaction patterns in MOOCs forums. A learning interaction discussion is constructed as a tree structured pattern and an efficient LIP-Miner algorithm is designed to find all frequent learning interaction patterns. In addition, studies are performed on mining discussion interaction patterns in MOOCs forums. We demonstrate via experiments that the propose algorithm can find interesting learning interaction patterns in MOOCs forums.