«Understanding students from a multi-modal perspective: empirical evidences»
Kshitij SharmaNorwegian University of Science and Technology (NTNU)
Abstract
Physiological data provides unprecedented access to the users’ behaviors, cognition and emotions. Multimodal data can be used as a tool to understand students’ states in various context, such as face to face classrooms, online education, problem-solving contexts, individual and collaborative learning and processes. This talk will focus on the learning contexts mediated by technologies. In this research professor Sharma has used multi=modal sensing technology to explain the different aspects of learning, for example, task-based performance, learning gains, experiences, socio-cognitive processes underlying the collaborative behaviour. He will present examples from multiple studies to show how multi-modal data in educational contexts can help us understand “how people learn?”. These studies include a diverse set of contexts, like, pair-programming, collaborative knowledge synthesis, intelligent tutoring systems, project based and informal learning. He will talk about defining physiological features and modelling them to explain the correlations and causality between learning processes and outcomes.
Biografía
Kshitij Sharma is a senior researcher at the Department of Computer Science at Norwegian University of science and Technology(NTNU). Kshitij Sharma’s research interests focus on using multimodal (mainly eye-tracking, dialogues, user actions, EEG) empirical data, and machine learning to understand collaborative and individual learning processes; and to design feedback tools to optimize the underlying processes. His research interests center on making sense of user experiences and practices to redesign and optimize interactive educational technologies. His goal is to understand why and how diverse learner categories (e.g., face-to-face, online, different expertise) use technologies in the ways that they do. Dr. Sharma has developed and experimented with games, tangible interfaces, robots, e-commerce and information systems, and collaborative technologies since 2011. On the methodological front he has worked with advance machine learning and statistical tools (Extreme Value Theory).
