Predicting stress levels in the Stress-Lysis dataset using Sliding Window approach

Abstract

The prevalence of depression, often exacerbated by heightened stress levels, is experiencing a significant surge, particularly among the youth, which correlates with an alarming rise in suicide rates within this demographic. This situation presents a compelling public health challenge that necessitates comprehensive investigation and intervention strategies. The present study aims to explore the utilization of a depression symptom database, employing classical machine learning techniques, with a focus on the Random Forest algorithm alongside other methodologies, to assess and diagnose stress levels. The objective is to facilitate timely interventions for individuals grappling with depressive symptoms. Accurate assessment of stress levels is essential for healthcare providers, as it enhances their ability to identify the mental health status of patients effectively and develop tailored treatment plans that may alleviate the severity of symptoms. This approach is particularly urgent in light of the concerning trends observed in mental health issues among younger populations.