Unveiling the Multifaceted Landscape of Social Media Usage and Mental Well-being

Abstract: The rapid rise of social media has raised concerns about its impact on mental health. Understanding user engagement and factors influencing social media usage is crucial. This study explores the link between social media patterns and mental well-being. Mental health issues are a global concern, with the WHO reporting that depression and anxiety cost $1 trillion annually in lost productivity. The World Bank highlights that urban areas, particularly affecting youth and working-age individuals, face severe mental health challenges due to lifestyle changes and social media, threatening societal well-being and economic stability. To better understand and predict the factors influencing mental health, we applied various classification techniques using machine learning algorithms. These included Random Forest, K-Nearest Neighbors and Logistic Regression. The models aimed to identify key predictors of mental health outcomes, focusing on features such as occupation, relationship status, and social media usage patterns. The analysis revealed that occupation and social media behaviors significantly affect mental health. Our findings suggest targeted interventions, like workplace wellness programs and social media usage guidelines, could mitigate adverse effects. This research highlights the importance of integrating technology with mental health strategies to improve outcomes and enhance quality of life. Keywords: Social Media Usage Patterns, Mental Well-being, Machine Learning Feature Importance, Distraction, Interventions