Over the last decade, there has been a renewed interest in leveraging new data collection tools for capturing students’ learning processes that go beyond the acquisition of conceptual knowledge. With an ever-increasing ease of access to information, educational researchers are more and more interested in teaching “21st century skills. Those skills include (but are not limited to) students’ curiosity, critical thinking, collaborative skills, grit, persistence or creativity. Having accurate and reliable tools for capturing them can pave the way for new kinds of instruction (for example by displaying levels of mastery to teachers through dashboards; by designing awareness tools for students; or by providing real-time, just-in-time, personalized feedback). To reach this goal, educational researchers are starting to use multimodal sensors and learning analytics to richly capture students’ behavior (i.e., through Multimodal Learning Analytics, MMLA). The goal of this project is to make a first step in this direction by exploring how galvanic skin response wristbands can capture proxies of 21st skills during learning activities. More specifically, we focus on capturing productive social interactions using physiological measures.
Figure 1: Directional Agreement (DA), Instantaneous Derivative Matching (IDM), Signal Matching (SM), and Pearson's Correlation (PC) are measures of physiological synchrony that can be derived from EDA (electrodermal activity) data.
Emily Yong Dich, Jake Cui, Iulian Radu, Bertrand Schneider
Dich, Y., Reilly, J. & Schneider, B. (accepted). Using Physiological Synchrony as an Indicator of Collaboration Quality, Task Performance and Learning. 12th International on Artificial Intelligence in Education.