This paper describes the potential and promising value of analytics on the emerging area of video-based learning. In particular, we describe the contributions presented at the International Workshop on Analytics on Video-based Learning (WAVe 2013) and envision the future of this research area. WAVe presents the current state-of-the-art in the design, development and evaluation of video-based learning systems. WAVe 2013 emphasized the importance and benefits of analytics for video-based learning to support learners and instructors with the appropriate resources for improving the use of video-based learning systems. The long term goal of WAVe is to develop a critical discussion about the next generation of analytics employed in video learning tools, the form of these analytics and the way they can be analyzed in order to help us to better understand and improve the value of video-based learning. In this volume, we have included the 6 submissions and the 2 keynote presentations that were featured at the workshop.
K.3.1 [Computers and Education]: Computer Uses in Education - Computer-Managed instruction (CMI).
With the widespread adoption of video-based learning systems such as Khan Academy and edX, new research in the area of Learning Analytics has emerged. Even new for-profit companies, such as Coursera and Udacity, have started offering forms of instruction that are primarily video-based. To date, universities across the globe (Stanford, Oxford, MIT and some 800 other schools) offer video lectures on topics from Algebra to Zoology.
The use of video for learning has become widely
employed in the past years [
Many instructors in higher education are implementing video lectures in a variety of ways, such as broadcasting lectures in real time, augmenting recordings of in-class lectures with face-to-face meetings for review purposes, and delivering lecture recordings before class to “flip the classroom” and provide hands-on activities during class time. Other uses include showing videos that demonstrate course topics and providing supplementary video learning materials for self-study.
Millions of learners enjoy video streaming from different
platforms (e.g., YouTube) on a diverse number of
devices (TV, desktop, smart phone, tablets) and thus
create records of billions of simple interactions. This
amount of learning activity might be converted via
analytics into useful information [
To explore the future of video-based technologies for teaching and learning, we aim to build a research community around this topical area, to brainstorm about what the next generation of video-based learning tools might look like, what kind of data can be collected, and how these data can help us to better understand and improve the value of video-based learning.
Existing empirical research (e.g. [
By taking into account learners' interactions and many other data—such as students' demographic characteristics of gender, ethnicity, English-language skills, prior background knowledge, their success rate in each section, their emotional states, the speed at which they submit their answers, which video lectures seemed to help which students best in which sections, etc. — new avenues for research in the intersection of video-based learning and analytics are now possible.
The workshop was structured be an interactive, engaging experience that motivated participants to get involved and engage in fruitful discussions on the topic of Video-Based Learning and the potential benefits of Analytics. To do so, it combined several activities. First, highly recognized keynote speakers opened the workshop. Then the workshop organizers gave the participants the opportunity to be engaged into creative and motivating discussions about the key issues related to analytics on video-based learning.
One of our main objectives was to bring together researchers who are interested on Learning Analytics and their application on video-based learning. Specifically, WAVe aimed to provide an environment where participants had opportunities to: develop their research skills; increase their knowledge base; collaborate with others in their own and complementary research areas; and discuss their own work. In particular, guiding questions and themes included:
What might next generation of analytics enhanced video learning tools look like? What kind of data can be collected from videobased learning tools? How these data can help us to better understand and improve the value of video-based learning?
The contributions of WAVe covered several topics, such as visualization techniques, video learning tools description, empirical examinations and best practices descriptions. In addition to the workshop proceedings (which are freely accessible from CEUR-WS), the presentations of WAVe are available via videolectures.net1.
In particular, Brooks et al., [
data aimed at understanding student re-watching behavior, temporal patterns for a single course, and how usage can be compared between groups of students.
Ronchetti [8] describes the current state of MOOCs and indicates that some already available tools can be better used for the extraction of semantic information from the videos. To this end, he proposes that we can improve the sensemaking of the information extracted from videos.
Ilioudi et al., [
applications for automated recording of lectures using mobile devices. These applications were developed based on the experiences gained by the ICTP Science Dissemination Unit (SDU) in Trieste, Italy with its open source “Enhance your Audience” (EyA) recording system2. ICTP has more than 10 thousands hours of automated educational recordings in the fields of physics and mathematics.
Viel et al., [12] give an overview of a system which
allows capturing a lecture to generate multi-video
learning object composed of synchronized videos,
audio, images and context information. In addition,
they present how a group of students interacted with a
learning object captured from a problem solving lecture
and give ideas of how navigation facilities and
visualization tools can assist us to include more
contextual information during the presentation.
Chorianopoulos and Giannakos [
The role of analytics on helping individuals to make sense of the learning procedures has drawn the interest of many scholars and practitioners in the last years. Analytics have proven their ability to help us to understand (make sense) many complex learning phenomena in the past [11].
However, comparing with research on text and discourse analytics, the research on video analytics is still on embryotic stage. Video analytics have an enormous potential, especially given what is currently happening around the explosion of MOOCs. As most of the MOOCs are using videos as their primary content delivery mechanism, research on MOOCs will heavily 2 wwww.openeya.org
influence video-based learning research. So we believe that the topic of WAVe is very timely with great potential. This potential will grow as MOOC platforms, like Coursera and Edx make their data publicly available to the research community.
Although research on video based learning has been
increased in the last years [
We would like to thank Dr. George Siemens and Dr. David Geerts for accepting our invitation to give keynote presentations, the workshop Program Committee members for contributing to the success of WAVe and the workshop chairs for their constructive comments and their helpful assistance throughout the workshop. Finally, we would like to thank http://videolectures.net/ for recording and editing the presentations of WAVe and the ERCIM "Alain Bensoussan" Fellowship programme for the financial support. [11] Siemens. G. 2012. Learning analytics: envisioning a research discipline and a domain of practice. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (LAK '12), 4-8.