Type: UROP
Status: Completed June 2022
Student: Daniele Gasparini

Studies in the lab have shown that affect recognition using physiological data is feasible with machine learning methods. Datasets collected in-the-wild can further improve such methods’ robustness and applicability. This study presents LAUREATE, a Longitudinal mUltimodal student expeRience datasEt for AffecT and mEmory research. The dataset was collected throughout a university semester with 44 participants (including two lecturers) in two courses totalling 52 sessions, including classes, quizzes, and exams. We recorded participants’ physiological signals with a wristband device and collected daily survey answers about participants’ behaviour (e.g., study hours, smoking habits, physical activity, caffeine and food intake) and their perceived engagement, attention, and emotions after class. As a proxy for evaluating the quality of the physiological data, we present preliminary findings about the relation between the physiological signals and the different session types.

For more information contact: Matías Laporte