Files
Abstract
The prevalence of mental health disorders is often undetected, leading to a serious issue which continues to affect all parts of society. Recurrent psychological patterns can be identified with the help of popular social networking websites. These patterns can depict ones thoughts and feelings in everyday life. Our research targets Twitter data to identify users who could potentially suffer from mental disorders, and classify them based on the intensity of linguistic usage and different behavioral features using sentiment analysis techniques. To confront the growing problem of mental disorders, we demonstrate a novel approach for the extraction of data and focus on the analysis of depression, schizophrenia, anxiety disorders, drug abuse and seasonal affective disorders. Our system can be used not only to identify, but also to quantify users' progression by following them on Twitter for a certain period of time. This can eventually help medical professionals and public health experts to monitor symptoms and progression patterns of mental disorders in social media users.