Development of Alternative Conception Diagnostic System based on Item Response Theory in MOOCs

Abstract

With the popularities of Massive Open Online Courses, a great number of enrollments in MOOCs generate much educational big data in terms of online activities and logs, which might be valuable for academia and practitioners. More personalized and intelligent online learning environment could be potentially created through educational data mining and learning analytics techniques. Based on Item Response Theory (IRT), the current study builds an item analysis system to identify alternative concepts/misconceptions from leaners’ response in exams. By calculating difficulty parameter and discrimination parameter from massive learners, our systems are believed to benefit both teaching faculties and online learners. With the affordances of the system, teaching faculties could assess leaners’ learning performance and quality of test items while alternative conception of leaners would be identified for strategic learning. Other practical and technical implications will be discussed in this paper.