Merging learner performance with browsing behavior in video lectures Konstantinos Chorianopoulos Abstract Department of Informatics Video lectures are nowadays widely used by growing Ionian University numbers of learners all over the world. Nevertheless, Corfu, GR-49100 Greece learners’ interactions with the videos are not readily choko@ionio.gr available, because online video platforms do not share them. In this paper, we present an open-source video Michail N. Giannakos learning analytics system. The system captures Department of Computer and learners’ interactions with the video player (e.g, pause, Information Science replay, forward) and at the same time it collects Norwegian University of Science information about their performance (e.g., cognitive and Technology (NTNU) tests) and/or attitudes (e.g., surveys). We have already Trondheim, NO-7491 Norway validated the system and we are working on learner michailg@idi.ntnu.no modeling and personalization through large scale data analysis. The tool is a freely available open source project for anyone to try and to improve. Author Keywords User Interactions, Video Based Learning, Education, Learning Analytics ACM Classification Keywords Copyright © 2013 for the individual papers by the papers' authors. H.5.2 [Information Interfaces and Presentation]: Copying permitted only for private and academic purposes. User Interfaces, user-centered design; K.3.1 This volume is published and copyrighted by its editors. [Computers and Education]: Computer Uses in WAVe 2013 workshop at LAK’13, April 8, 2013, Leuven, Belgium. Education - Computer-managed instruction (CMI). 38 Introduction started to be used in order to provide educators with The use of videos for learning has become widely valuable information about students (Figure 2). employed in the past years [3]. Most of the universities However, the usage of LA on video based learning it is and digital libraries have incorporated video into their still on embryotic research stage. instructional materials. Currently, Massive Online Open Courses (MOOCs) are becoming an increasingly important part of education. In order to support video Video Analytics System learning, various technological tools have been Custom player developed. For example, Matterhorn and Centra are GAE application YouTube buttons and just few of them. However, information from the video- logic and data- Chrome-less user activity base player loging with Java- based learners’ behavior and navigation is not yet script freely available to the educational technology community. Figure 3. Video analytics system architecture is modular and cloud- based. Web-based video systems might employ the open-source application Figure 2. Khan academy provides the teacher with a dashboard logic, in order to dynamically identify that depicts the performance of students across topics, but it rich information segments does not link the performance within the respective video sections. The purpose of this paper is to present an open-source video learning analytics system. The system facilitates the analysis of video learning behavior by capturing learners’ interactions with the video player (e.g, seek/scrub, play, pause) and collecting information for their performance (e.g., cognitive tests) and attitudes (e.g., surveys). Figure 1 Matterhorn provides an annotated seek-bar in order to improve navigation within a video lecture, but there is no Open-Source Video Learning Analytics support for collecting and analyzing learners navigation System Capturing and sharing analytics in emerged learning Learners’ interactions with the videos are not readily technologies can clearly provide scholars and educators available, because online video platforms do not share with valuable information. Specifically for the case of or they are not interest on them. In order to be able to video based learning, information obtained from learner capture and store these interactions, we developed an (hereinafter Learning Analytics-LA) have recently open-source video learning analytics system. Our system facilitates the analysis of video learning 39 behavior by capturing learners’ interactions with the is to replay the last 30 seconds of the video, while the video player (e.g, play, pause). Skip30 button jumps forward 30 seconds and its main purpose is to skip insignificant video segments. The For developing the Open-Source Video Learning main reason for developing these functions is to Analytics1 System (Figure 3), we used the Google App identify the video segments which learners’ consider as Engine (GAE) cloud platform and the YouTube Player important (repeated views). We decided to use buttons API [4]. There are several benefits of the selected tools that are similar to the main controls of VCR remote (GAE, YouTube, Google accounts). GAE enables the controls because they are familiar to users. In addition, development of web-based applications, as well as questionnaires and performance tests can be employed maintenance and administration of the traffic and the next to the main interface of the player (Figure 4) and data storage. YouTube allows developers to use its the respective data will be integrated in the Data Store. infrastructures (e.g., YouTube videos) and provides chrome-less user interface, which is a YouTube video player without any controls. This facilitates customization within Flash or HTML 5. As such, we used JavaScript to create custom buttons and to implement their functions. Additionally, learners’ used Google account in order to sign in and watch the uploaded videos. In this way, we accomplished user authentication and we avoid the effort of implementing a user account system just for the application. Thus, users’ interactions are recorded and stored in Google’s database alongside with their Gmail addresses. The Google App Engine database (Data store) is used to store the interactions. Each time someone signs in the web video player application, a new log is created. Whenever a button is pressed, an abbreviation of the button’s name and the time it occurred are stored. Figure 4. The interface of the system has familiar buttons, as well as questionnaire functionality The video player (Figure 4) employs custom buttons, in order to be simple to associate user actions with video semantics. We have modified the classic forward and backward buttons to “Skip30” and “Replay30”. The first one jumps backwards 30 seconds and its main purpose 1 Open source project: https://code.google.com/p/socialskip/ 40 Figure 4. An Example of Learner Activity Visualization The system is also providing all these interactions in an (i.e., [5]) to understand and leverage actual learner form which can be easily visualized, using for example experience. In addition, to the best of our knowledge times series (Figure 5). To this end, researchers and there are no efforts using LA from diverse sources in scholars are being able to extract all the rich order to triangulate them and derive valuable information and understand better the learner information about students. behavior. In addition, the results from the questionnaires and performance tests can be used to In that paper we present an open-source video learning triangulate the results. By taking into account learners' analytics system. Although we designed the system as interactions and many other data—such as their a web-based one, the concept of mapping implicit demographic characteristics, prior background learner interactions to a time-series for further analysis knowledge, their success rate in each section, their has a much broader application. emotional states, the speed at which they submit their answers, which video lectures seemed to help which This large amount of LA produced during the interaction students best in which sections, etc.— we will be able of the learner with video-based learning system can be to understand how this medium is being used by the converted into useful information for the benefit of all students and proceed to the appropriate amendments video learners. As long as learners' watching videos on to the current video based learning systems and Web-based systems [1], more and more interactions practices. are going to be gathered and therefore, dynamic analysis would represent in a timely fashion the most Benefits and Perspectives important (rich-information) segments of a video Many corporations and academic institutions are according to evolving learner interests. We also expect making lecture videos and seminars available online, that the combination of richer user profiles and content there have been few and scattered research efforts 41 metadata provide opportunities for adding value to LA References obtained from video based learning. [1] Brooks, C et al.: OpenCast Matterhorn 1.1: reaching new heights. 2011. In Proceedings of the 19th ACM international conference on Multimedia (MM '11). By taking into account learners' interactions and many ACM, New York, NY, USA, 703-706. other data—such as students' demographic [2] Butin. D. W. 2012. What MIT Should Have Done. characteristics of gender, ethnicity, English-language eLearn. 6, pages. doi:10.1145/2241156.2263018 skills, prior background knowledge, their success rate in each section, their emotional states, the speed at [3] Giannakos, M.N. 2013. Exploring the video-based learning research: A review of the literature. British which they submit their answers, which video lectures Journal of Educational Technology, Wiley. seemed to help which students best in which sections, [4] Leftheriotis, I., Gkonela, C., & Chorianopoulos, K. etc.— new avenues for research are opening. As Butin 2012. Efficient Video Indexing on the Web: A System [2] clearly articulated in ACM eLearn, using students’ That Crowdsources User Interactions with a Video data, we can feed powerful algorithms and create Player. User Centric Media, Springer, 123-131. seemingly personalized feedback [6]. Future work will [5] Ketterl, M., Emden, J., and Brunstein, J. r. 2008. help to collect diverse LA (i.e., success rate, emotional Social Selected Learning Content Out of Web Lectures. states), which will allow the community to consider the In: Proceedings of The 19th ACM Conference on challenges for developing a “recommender system”, Hypertext & Hypermedia, 231-232. which we have all encountered on Amazon. Such a [6] Ronchetti, M. 2010. Using video lectures to make system would have allowed video lectures to discover teaching more interactive, International Journal of that perhaps certain lecture characteristics and Emerging Technologies in Learning (iJET), 5 (2), 45-48. practices, help some students more effectively at different points in a course. The intellectual merit of this proposal is the development of a novel experimental video analytics system. The presented tool aims to contribute to the area, by providing an open source solution for video analytics capturing (the first of its kind to the best of our knowledge) for further improvement and experimentation. Acknowledgements The authors would like to express their gratitude to Ioannis Leftheriotis and Chrysa Gkonela for their contribution on that research. 42