Publication Details
Konstantinos Chorianopoulos, Michail Giannakos, Nikos Chrisochoides and Scott Reed.
Published in 14th IEEE International Conference on Advanced Learning Technologies, (ICALT 2014), 2014
Abstract
Video learning analytics are not open to education stakeholders, such as researchers and teachers, because online video platforms do not share the interactions of the users with their systems. Nevertheless, video learning analytics are necessary to all researchers and teachers that need to understand and improve the effectiveness of the video lecture pedagogy. In this paper, we present an open video learning analytics service, which is freely accessible online. The video learning analytics service (named SocialSkip) facilitates the analysis of video learning behavior by capturing learners’ interactions with the video player (e.g., seek/scrub, play, pause). The service empowers any researcher or teacher to create a custom video-based experiment by selecting: 1) a video lecture from YouTube, 2) quiz questions from Google Drive, and 3) custom video player buttons. The open video analytics system has been validated through dozens of user studies, which produced thousands of video interactions. In this study, we present an indicative example, which highlights the usability and usefulness of the system. In addition to interaction frequencies, the system models the captured data as a learner activity time series. Further research should consider user modeling and personalization in order to dynamically respond to the interactivity of students with video lectures.
