|
Abstract:
|
Stress management is a pervasive issue in the modern high schooler's life. Despite many efforts to support teenagers’ mental well-being, teens often fail to recognize signs of stress until their emotions have escalated. Being able to identify early signs of high stress, anxiety, and “low” feelings and predict their onset using physiological signals collected passively in real-time could help teens improve their awareness of their emotional well-being and take a more proactive approach to managing their emotions. Using data collected by the Empatica E4 wearable device from seven teens, we developed several predictive models and systematically compared their performance. Using these models, we identified key physiological signals that are predictive of the onset of stress and negative psychological states in teens. We find that the participant-specific models vary considerably among individuals but are reasonably good at detecting early signs of stress in each participant.
|
