Utilizing Machine Learning for Self Assessment of Mental Well-being, Informed by Expert Insights and Student Experiences

Abstract

Monitoring one's own well-being is of utmost importance in bolstering mental health. Recent research involving college student populations has investigated the long-term feasibility of recording daily emotional states, activities, and social interactions. The prevalence of mental health issues is on the rise, particularly among young adults and adolescents, placing university students at a heightened risk due to challenges related to fitting in and forming connections in diverse social environments. Many students experience feelings of not belonging, which can significantly impact their mental wellness. Additionally, the fear of being stigmatized as mentally unwell by their peers often deters students from seeking professional assistance. Our project seeks to offer a self-reliant solution to address these challenges, enabling students to gain a better understanding of their emotions and providing them with tasks and strategies, facilitated by machine learning, to alleviate their mental burdens.