Mental states and personality based on real-time physical activity and facial expression recognition

• DOI: 10.3389/fpsyt.2022.1019043
• Publication Date: 2023-01-09T08:43:47Z
• Authors: Yating Huang; Dengyue Zhai; Jingze Song; Xuanheng Rao; Xiao Sun; Jin Tang
• Keywords: Facial expression recognition

Introduction To explore a quick and non-invasive way to measure individual psychological states, this study developed interview-based scales, multi-modal information was collected from 172 participants. Methods We the Interview Psychological Symptom Inventory (IPSI) which eventually retained 53 items with nine main factors. All of them performed well in terms reliability validity. used optimized convolutional neural networks original detection algorithms for recognition facial expressions physical activity based on Russell's circumplex model five factor model. Results found that there significant correlation between scale participants' scores each Checklist-90 (SCL-90) Big Five (BFI-2) [ r = (−0.257, 0.632), p < 0.01]. Among data, arousal significantly correlated interval validity ( 0.01), valence IPSI SCL-90, gender, age, factors scales. Discussion Our research demonstrates mental health can be monitored assessed remotely by collecting analyzing multimodal data individuals captured digital tools.