Personalized Student Stress Prediction with Deep Multitask Network

• DOI: 10.48550/arxiv.1906.11356
• Publication Date: 2019-01-01
• Authors: Abhinav Shaw; Natcha Simsiri; Iman Deznaby; Madalina Fiterau; Tauhidur Rahaman
• Keywords: Popularity; Predictive modelling

With the growing popularity of wearable devices, ability to utilize physiological data collected from these devices predict wearer's mental state such as mood and stress suggests great clinical applications, yet a task is extremely challenging. In this paper, we present general platform for personalized predictive modeling behavioural states like students' level stress. Through use Auto-encoders Multitask learning extend prediction both sequences passive sensor high-level covariates. Our model outperforms state-of-the-art in mobile data, obtaining 45.6 % improvement F1 score on StudentLife dataset.