Скачать или смотреть Knowledge-Aware Suicide Risk Prediction

Self-harm and suicidal behaviors are preventable if the risk can be identified early. It is critical to incorporate external knowledge to enhance suicide prediction performance. In this talk, Dr. Qingpeng Zhang will introduce recent research on developing knowledge-aware suicide risk prediction models in different contexts. Dr. Zhang will overview a patient embedding method, Dx2Vec (Diagnoses to Vector), based on the comorbidity network constructed by all historical diagnoses. He will also discuss a knowledge-aware natural language processing model to identify help-seekers at a high suicide risk by mining their counseling conversations. Experiments with the data of a major Cantonese mental health counseling platform demonstrate that the model significantly outperformed state-of-the-art NLP models by incorporating domain knowledge. The findings have the potential to be translated into effective self-harm/suicide prevention programs.