Abstract

MOOCs make extensive use of videos. Students interact with them by pausing, seeking forward or backward, replaying segments, etc. We can reasonably assume that students have different patterns of video interactions, but it remains hard to compare student styles of video interactions. Some methods were developed, such as Markov Chain and edit distance between event sequences. However, these methods ignore the time spent between events. This paper proposes a new methodology of comparing video sequences of interaction based both on time spent in each state and the succession of states by computing the distance between the transition matrices of the video interaction sequences. The proposed methodology can measure the level of similarity of interaction between two video sequences of interaction and determine if two different viewers have the same video interaction style. The aim of this research is to identify patterns that lead to success or failure when listening to videos in an online course. Another possible for online applications is to classify video listening styles, which would improve the accuracy of recommendations according to the video listening style.

Download

Share

COinS