Julpan Daniel Simatupang
Universitas Sumatera Utara

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

Found 1 Documents
Search

Predictive Analysis for the Early Detection of Depression in Adolescents Based on Social Media Usage Patterns Genesis Sembiring Depari; Julpan Daniel Simatupang
Formosa Journal of Computer and Information Science Vol. 5 No. 1 (2026): March 2026
Publisher : PT FORMOSA CENDEKIA GLOBAL

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55927/fjcis.v5i1.16904

Abstract

This study examines the use of predictive analytics for the early detection of depression among teenagers based on social media usage patterns and behavioral indicators. The research utilizes a secondary dataset consisting of 1,200 adolescent records, including variables such as daily social media usage duration, sleep duration, stress level, anxiety level, addiction tendency, academic performance, physical activity, and depression classification labels. A quantitative approach was applied using machine learning algorithms, including Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine. The dataset was processed through data cleaning, encoding, normalization, exploratory data analysis, feature selection, model development, and model evaluation. The results show that sleep duration, daily social media usage, stress level, anxiety level, and academic performance are important predictors of teen depression.