Towards Intention Understanding in Suicidal Risk Assessment with Natural Language Processing

Abstract

Recent applications of natural language processing techniques to suicidal ideation detection and risk assessment frame the detection or assessment task as a text classification problem. Recent advances have developed many models, especially deep learning models, to boost predictive performance. Though the performance (in terms of aggregated evaluation scores) is improving, this position paper urges that better intention understanding is required for reliable suicidal risk assessment with computational methods. This paper reflects the state of natural language processing applied to suicide-associated text classification tasks, differentiates suicidal risk assessment and intention understanding, and points out potential limitations of sentiment features and pretrained language models in suicidal intention understanding. Besides, it urges the necessity for sequential intention understanding and risk assessment, discusses some critical issues in evaluation such as uncertainty, and studies the lack of benchmarks.

Prompt engineering for digital mental health: a short review

“…Nguyen et al ( 45 ) proposed a novel depression screening process based on out-of-domain knowledge transfer methods. Ji ( 10 ) introduced an NLP-based suicidal risk detection method based on the sentiment classification capability of LLMs. Gupta et al ( 46 ) explored the LLMs' zero-shot performance on unseen dialogue-related NLG tasks and cross-task generalization in multiple dialogue settings.…”