Related Experiment Video
Updated: Nov 23, 2025

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
Published on: July 31, 2016
Identifying Psychological Symptoms Based on Facial Movements
Xiaoyang Wang1,2, Yilin Wang1,2, Mingjie Zhou1,2
1Institute of Psychology, Chinese Academy of Sciences, Beijing, China.
Facial movements can predict multi-dimensional mental health status using Symptom Checklist 90 (SCL-90) scores. This study validates facial prediction models for mental health assessment, showing good reliability and criterion validity.
Area of Science:
- Psychiatry
- Computer Science
- Psychology
Background:
- Existing mental illness detection methods often focus on single conditions.
- A comprehensive, multi-perspective assessment of mental health is more beneficial in non-professional settings.
- This study explores the potential of facial analysis for broader mental health evaluation.
Purpose of the Study:
- To develop and validate facial prediction models for assessing multi-dimensional mental health.
- To evaluate the criterion validity, convergent validity, discriminant validity, and reliability of these models.
- To determine if fine-grained mental health aspects can be identified from facial movements.
Main Methods:
- Recruited 100 participants for the study.
- Assessed multi-dimensional psychological symptoms using the Symptom Checklist 90 (SCL-90).
- Recorded facial movements using Microsoft Kinect, extracting time-series characteristics for model input.
Main Results:
- Facial prediction models demonstrated good criterion validity with significant correlation coefficients (0.26 and 0.42, P < 0.01).
- Models exhibited high convergent validity but low discriminant validity, except for depression.
- Split-half reliability was good across all models, ranging from 0.516 (hostility) to 0.817 (interpersonal sensitivity) (P < 0.001).
Conclusions:
- The validity and reliability of facial prediction models for mental health measurement, based on SCL-90, were confirmed.
- Facial analysis can identify nuanced aspects of mental health.
- This research offers a feasible method for multi-dimensional mental health prediction using facial data.
Related Concept Videos
Facial Feedback Hypothesis
Muscles for Facial Expressions
Prosopagnosia
Causes of Social Behavior I: Actions and Characteristics of Individuals
Accessory Structures of the Eye
Therapeutic Communication
Verbal communication depends on language or a prescribed way of using words so that people can share information effectively. The critical aspects of verbal...

