Multimodal Behavioral Dataset of Depressive Symptoms in Chinese College Students–Preliminary Study

In this paper, we present a multimodal dataset that includes simultaneous action, expression, and speech information for Chinese college students with and without depressive symptoms. We collected the data with two cameras and five microphones in a controlled environment. In addition, we conducted two screening surveys, namely, the Beck Depression Inventory-II (BDI-II) and Center for Epidemiologic Studies Depression Scale (CES-D, used to crosscheck the BDI-II scores), to provide estimated depression severity scores, for use as ground truth. The experimental procedure involved two main steps: interviewing each participant and recording the participants’ speech. Then, we extracted a set of behavioral features, which can be used to analyze the relationship between Chinese college students’ depressive symptoms and their observed behavior.