DETECTING MENTAL DISORDERS USING EMOTIONAL PATTERNS FROM SOCIAL MEDIA

AbstractMillions of people around the world suffer from mental disorders that significantly affect their thoughtsand behaviors. Detecting these conditions in a timely manner is both challenging and vital, as earlyintervention can offer critical support before the illness worsens. A promising strategy for earlydetection involves analyzing how individuals express themselves, particularly through writing andsocial media activity. This article explores two computational models developed to identify theexistence and variations of emotions expressed by users on social media.The analysis is based on tworecent public datasets related to eating disorders and depression. The outcome demonstrate that theproposed emotional representations effectively capture key indicators of these mental healthconditions. Furthermore, combining both models improves performance—matching the most effectivetechnique for identifying depression and coming within 1% of the top-performing approach foranorexia. In addition, these models show potential for enhancing the interpretability of the outcomes. Keywords: Emotional patterns, mental illnesses, and machine learning