Abstract:
Mental wellness encompasses emotional, psychological, and social well-being that influences our ways of thinking, emotions, and actions. Any mental health conditions may impair people’s everyday life. University-going students experience additional obstacles in disclosing mental health issues in open talks owing to stigma and privacy threats. However, they show mental health-relevant signals on social networking networks. In most situations, researchers or psychiatrists try to figure out the mental health issues of students utilizing longitudinal studies from their self- reported data that may be error-prone, prejudiced, and expensive & time-consuming. In this study, we examine both self-reported survey data and social media data to identify the underlying elements and reasons behind mental health issues (i.e., anxiety, stress, depression, and suicide ideation or suicidality) of students. It will also show how social media data analysis may be more robust in uncovering fresh and valuable insights connected to mental health illnesses. We intend to find related factors with mental health disorders of Bangladeshi university students from their self-reported data and create classification & regression models for predicting mental health disorder levels and scores, respectively, employing the associated factors. Then, we offer a unique topic modeling technique in Bangla for analyzing social media data and, lastly, explore social media data to acquire valuable knowledge related to mental health diseases. In most situations, the insights from the social media data complement the conclusions from the self-reported survey data. However, social media data analysis exposes fresh insights that are more valuable than survey data analysis. Moreover, the social media data analysis validates the upward and downward trends in the mental health disorder scores owing to diverse events (i.e., political turmoil, demonstrations or movements, disasters, pandemics, etc.) across time.