Evaluating Mental Well-being in Youth: Identification and Diagnostic Tools

Evaluating Mental Well-being in Youth: Identification and Diagnostic Tools

Thara K L

Assistant Professor

Department of ISE

JNNCE, Shivamogga

Karnataka, India

taraklokappa@gmail.com

Sunilkumar H R

Assistant Professor

Department of CS&E

PESITM, Shivamogga

Karnataka, India

sunilhr@pestrust.edu.in

Abstract

The COVID-19 pandemic significantly affected global mental health, intensifying existing issues and introducing new challenges. Mental health is often overlooked due to stigma and cultural norms, and during the pandemic, much of the attention and resources were focused elsewhere. In response, a machine learning-based system was developed to specifically detect anxiety and depression. Various algorithms, such as random forest, logistic regression, KNN, Naïve Bayes, and SVM, were evaluated for their effectiveness in identifying these mental health conditions. The system utilizes a trained machine learning model alongside a questionnaire to identify early signs of mental health concerns. Being web-based, the tool has the potential to reach a global audience, offering a broader approach to addressing mental health. Early detection through this system allows for timely interventions and treatments, ultimately improving mental well-being.

Keywords: Data science, Machine learning, Anxiety, Depression, and Mental health detection