Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Indonesian Journal of Artificial Intelligence and Data Mining
Salsabila, Meidita
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Development of a CNN-Based Mental Health Consultation Application Integrating Facial Expressions and DASS-42 Questionnaire Salsabila, Meidita; Lindawati, Lindawati; Fadhli, Mohammad
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 2 (2025): July 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i2.37525

Abstract

Early detection of psychological disorders such as Depression, stress, and anxiety is still limited due to a lack of awareness and inadequate access to mental health consultation services. This study aims to develop a mental health consultation application that utilizes facial expressions and the Depression, Anxiety, and Stress Scale (DASS-42) questionnaire, employing a Convolutional Neural Network (CNN) algorithm. The CNN algorithm is used to detect and classify facial expressions into emotional categories, such as anger, sadness, disgust, and fear,  as early indicators of mental conditions. In addition, the DASS-42 questionnaire provides a structured psychological assessment to determine the severity of Depression, anxiety, and stress. This combination offers a more comprehensive and accurate evaluation, thus bridging the gap in early detection methods for mental health. Based on the development and testing results, a mental health consultation app utilizing facial expressions and the DASS-42 questionnaire was successfully created by using the CNN algorithm as a facial expression detector. The system can identify facial expressions such as sadness, anger, disgust, and fear with an accuracy of 81%, showing excellent performance in detecting early signs of mental disorders.
Co-Authors Fadhli, Mohammad Lindawati Lindawati