Profiling instructor activities using smartwatch sensors in a classroom

During a classroom session, an instructor performs several activities, such as writing on the board, speaking to the students, gestures to explain a concept. A record of the time spent in each of these activities could be valuable information for the instructors to virtually observe their own style of instruction. It can help in identifying activities that engage the students more, thereby enhancing teaching effectiveness and efficiency. In this work, we present a preliminary study on profiling multiple activities of an instructor in the classroom using smartwatch sensor data. The proposed approach uses data from available sensors in the smartwatch and builds a machine learning model to predict the activities of an instructor. We use a benchmark dataset that was collected in the wild to test out the feasibility of classifying the activities. Different machine learning models are used and the results are compared using multiple metrics to show the efficacy of predictive modeling in automatic classroom observation of instructors.