IDENTIFYING BEHAVIORAL PATTERNS IN MOOC VIDEO ENGAGEMENT USING CLUSTERING APPROACH

Abstract

Videos are the core components of MOOCs for delivering course content and teaching the core concepts effectively. While the literature provided strong and consistent evidence regarding the link between video engagement and the success in MOOCs, the research on video engagement behavior is still emerging and in demand of further research. This research aims to contribute to the literature by identifying behavioral patterns of video engagement in a MOOC and reveal the association of these patterns with success and failure. In particular, we employed simple video engagement metrics with an attempt to identify clusters of behavioral patterns that can be applied to different contexts. Acknowledging that students may exhibit varied engagement behaviors across study sessions, a session-level clustering analysis was performed, differently from previous research. After applying K-Means clustering algorithm, three clusters of behavioral patterns were identified: static viewing (the most predominant behavior), in which students viewed videos with minimal interactions; engaged viewing, involving high frequency of play and pause events; and focused viewing (the least frequent pattern), which involved mainly seeking the video for specific information. While video sessions with static viewing were very common among both high and low achieving students, most engaged-viewing sessions or focused-viewing sessions consistently belonged to the successful students. In addition, successful students were found to demonstrate multiple viewing behaviors, suggesting their effort in using multiple strategies while watching videos. Based on the findings, the paper discusses implications for the design of MOOCs and other online learning platforms that support video-based learning.