Multimodal data to design visual learning analytics for understanding regulation of learning

Abstract

The increased interest in multimodal data collection in the learning sciences demands for new and powerful methodological and analytical techniques and technologies. It is especially challenging for learning scientists to handle, analyse, and interpret complex and often invisible multimodal data when investigating regulation of learning in collaborative settings as this data can be cognitive, social and/or emotional in nature, much of which is covert in nature. The aim of this paper is to present ways to simplify the analysis and use of rich multimodal data by learning scientists. This is done by making primarily invisible regulation processes and their accompanying social and contextual reactions visible, measurable, and ultimately interpretable. To facilitate data visualisation and processing with respect to the regulation of learning, a Graphical User Interface (GUI) known as SLAM-KIT has been designed. SLAM-KIT reveals principal features of complex learning environments by allowing users to travel through the learners' data and its statistical characteristics. This kit has practical implications as it simplifies complex information and data while making them available through visualisation and analysis to the researchers. Our short-term goal is to simplify this tool for the teachers and learners.