Abstract—Massive Open Online Courses (MOOC) are an emerging technology for online teaching and learning at a larger scale. Therefore getting an overall view of student behavior and performance is quite challenging. We intend to provide a solution by identifying the learner behavior using click stream interaction analysis.
In MOOCs, videos provide the most informative content of learner behavior because majority of the students gather knowledge from videos whereas a relatively fewer number of students participate in assignments and forum activities. In this research the click stream data from the video interactions were analyzed to understand the learner behavior. The interactions such as play, pause, seeks and speed changes were aggregated to calculate features which indicate frequency and temporal dynamics of the behavior of the students. Two courses Engineering CS101 and Humanities and Statistical Learning from a dataset of the edX platform were analyzed by using unsupervised learning. The findings from this research can be used to understand how the learner behavior in MOOC videos differs in two different courses.
Index Terms—E-learning, learner behavior, unsupervised learning.
The authors are with the Department of Computer Science and Engineering, University of Moratuwa, Sri Lanka (e-mail: firstname.lastname@example.org, email@example.com, firstname.lastname@example.org, email@example.com, firstname.lastname@example.org, email@example.com).
Cite: D. Dissanayake, T. Perera, C. Elladeniya, K. Dissanayake, S. Herath, and I. Perera, "Identifying the Learning Style of Students in MOOCs Using Video Interactions," International Journal of Information and Education Technology vol. 8, no. 3, pp. 171-177, 2018.