Examining Social Media Posts for Identification of Anxiety and Depression Utilizing Machine Learning Techniques

The prevalence of mental diseases like depression and anxiety among students has become a growing concern in recent years. With the widespread use of social media platforms, individuals often express their emotions, thoughts, and experiences through posts and interactions. This paper investigates the feasibility of classifying students' anxiety and depression based on the content of their social media posts. Recently, some research communities in various domains have shown enthusiasm for investigating the potential of leveraging social media platforms for extracting valuable insights for decision-making and creative knowledge. Social media has been utilized to aid software development activities, analyze cryptocurrency trends, identify network communities, and make recommendations, among others. Apart from other fields within the eHealth domain, the application of social media platforms and the sophisticated analysis of extensive datasets to anticipate mental health disorders like depression, schizophrenia, eating disorders, anxiety, and addictive tendencies has garnered substantial attention and interest. However, one of the challenges lies in either having enough historical data or regular monitoring of a patient's activities to identify a person's mental health condition using traditional methods. To tackle this concern, we introduce an approach aimed at categorizing individuals with past mental health conditions through the utilization of information sourced from a widely-used social media platform such as Facebook.