Reporter：Michael Chau
Abstract：Title: Depression Detection on Social Media
How to manage and provide appropriate treatment to people suffering from depression and emotional distress is a pressing issue. However, many people with depression and emotional distress are not sufficiently recognized and treated; they do not proactively seek help either. Therefore, it is highly desirable to devise a method to effectively and proactively identify these people. Following the design science approach, we propose a novel design called DKMAN (which stands for Domain Knowledge-enhanced Mutual Attention Network) based on deep learning and a knowledge-enhanced mutual attention mechanism to identify people with depression and emotional distress. Our model incorporates both general knowledge and domain knowledge in the learning process through language representations and mutual attention mechanism. The research has important academic contributions and practical implications for depression detection.
