Introduction
Background
Video-based learning
Video learning analytics
Smart video-based learning
Contributions on smart video learning analytics
Smart video learning analytics for open educational resources
Collaborative video annotation resources for smart video learning analytics
Smart video-based learning ecosystem to support active learning
Design considerations for interactive question-enhanced video lectures
Towards smart-interactive affordances in video-based learning environments
The role of data science methods
Open research questions - guiding objectives
Smart learning analytics research dimensions
Learning Analytics | Affordances | Content | Practices & pedagogies | Assessment functionalities | Main design challenges | Expected results/outcome |
---|---|---|---|---|---|---|
-sequence analytics -related with student’s baseline -analytics related with the produced artifacts (artifacts analysis) -combined analytics coming from different streams (e.g. both the video and platform) -progress related analytics -analytics assisting in adaptation (adaptive LA) -ready to be visualized analytics | -support input from both the students and the teachers (e.g., annotations) -integration of the digital textbooks affordances (e.g., search) -related with the control of the learning process -intuitive typical video controls (e.g., rewind) -dynamic visualizations -relaxation of constraints in time and space -adaptive content and navigation | -“how to” video resources are most appropriate -the content of the video is very much related with the type of the video (e.g., documentaries, lecture style, khan style) -worked problems/ examples -hard to describe/ easy to visualize content -abstract knowledge -abstract and procedural knowledge -Science concepts (e.g., chemistry, mechanical engineering, programming) | -active and self-regulated learning practices -storytelling practices -use different modalities -avoid splitting attention -generalization effect (e.g., knowing when to use assessment) -apply gamification principles and reward students to keep them motivated | -robust and well-designed peer-review functionalities -review and critique (based on taught process) -multiple choice or other immediate feedback assessment for the basic knowledge/ concepts -integrate additivity in assessments (if possible) -visualizations to make assessment intuitive and inform students’ for their progress with a simple glance | -seamless integration of different elements (e.g., videos, assessment) -support deep and deep learning functionalities within the videos -interoperable design (information exchange between different elements) -integrate open ended questions -intuitively guide students to explore the learning materials -accommodate adaptive design (progressive enhancement) and adaptation affordances | -seamless integration of different elements (e.g., videos, assessment) -support deep and deep learning functionalities within the videos -interoperable design (information exchange between different elements) -integrate open ended questions -intuitively guide students to explore the learning materials -accommodate adaptive design (progressive enhancement) and adaptation affordances |