Detecting People Interested in Non-Suicidal Self-Injury on Social Media
This addresses a mental health monitoring problem for social media platforms, but it is incremental as it applies existing methods to a new domain.
The paper tackled detecting individuals interested in Non-Suicidal Self-Injury on social media by using a supervised binary classification approach based on self-declared interests, and demonstrated its effectiveness on a real-world dataset from LiveJournal.
We propose a supervised learning approach to detect people interested in Non-Suicidal Self-Injury (NSSI). We treat the task as a binary classification problem, and build classifiers based upon features extracted from people self-declared interests. Experimental evaluation on a real-world dataset, the LiveJournal social blogging networking platform, demonstrates the effectiveness of our proposed model.