Machine learning-driven insights into social media's influence on student mental health and academic stress: research trends, challenges, and future directions

Social media's growing pervasiveness in students' daily life has raised serious concerns about psychological health in addition to providing previously unheard-of chances for interaction. Social media's introduction has had a profound impact on how students communicate, learn, and view academic difficulties. Although these platforms make it easier to communicate, collaborate, and share material, they also come with concerns including information overload, social comparison, and distraction, all of which can lead to academic stress. The relationship between social media use and student mental health is examined in this survey paper, which highlights the ways in which different methods are being applied to assess, forecast, and potentially lessen psychological distress in academic populations. The study investigates how data-driven approaches and Machine Learning (ML) could be used to spot stressful trends in online behavior. We have highlighted research gaps and offer future options for creating successful interventions and frameworks for digital well-being by examining recent literature. Additionally, this study summarizes previous research on machine learning models intended to identify, forecast, and comprehend mental health issues in students based on their interactions on social media.