EMNLP Findings2022
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Improving the Generalizability of Depression Detection by Leveraging Clinical Questionnaires cites Do Models of Mental Health Based on Social Media Data Generalize?
- Towards Interpretable Mental Health Analysis with Large Language Models cites Improving the Generalizability of Depression Detection by Leveraging Clinical Questionnaires
- Identifying Moments of Change from Longitudinal User Text cites A Time-Aware Transformer Based Model for Suicide Ideation Detection on Social Media
- SeD-UD: An Influence-Driven and Hierarchically-Decoupled Information Bottleneck for Multimodal Intent Recognition cites Contextual Augmented Global Contrast for Multimodal Intent Recognition
Cited by top-tier papers3
- Towards Interpretable Mental Health Analysis with Large Language ModelsKailai Yang, Shaoxiong Ji, Tianlin Zhang, Qianqian Xie et al.EMNLP 2023 · 114 citations
- Contextual Augmented Global Contrast for Multimodal Intent RecognitionKaili Sun, Zhiwen Xie, Mang Ye, Huyin ZhangCVPR 2024 · 19 citations
- SeD-UD: An Influence-Driven and Hierarchically-Decoupled Information Bottleneck for Multimodal Intent RecognitionQin Li, Wenbo Zhang, Limei Liu, Han Peng et al.CVPR 2026
Builds on4
- A Time-Aware Transformer Based Model for Suicide Ideation Detection on Social MediaRamit Sawhney, Harshit Joshi, Saumya Gandhi, Rajiv Ratn ShahEMNLP 2020 · 97 citations
- Improving the Generalizability of Depression Detection by Leveraging Clinical QuestionnairesThong Nguyen, Andrew Yates, Ayah Zirikly, Bart Desmet et al.ACL 2022 · 66 citations
- Identifying Moments of Change from Longitudinal User TextAdam Tsakalidis, Federico Nanni, Anthony Hills, Jenny Chim et al.ACL 2022 · 46 citations
- Do Models of Mental Health Based on Social Media Data Generalize?Keith Harrigian, Carlos Alejandro Aguirre, Mark DredzeEMNLP Findings 2020 · 45 citations
Related papers
- PsyGUARD: An Automated System for Suicide Detection and Risk Assessment in Psychological CounselingHuachuan Qiu, Lizhi Ma, Zhenzhong LanEMNLP 2024 · 3 citations
- Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical EvaluationTong Li, Shu Yang, Junchao Wu, Jiyao Wei et al.EMNLP Findings 2025 · 9 citations
- What's the Meaning of Superhuman Performance in Today's NLU?Simone Tedeschi, Johan Bos, Thierry Declerck, Jan Hajic et al.ACL 2023 · 12 citations
- An Annotated Dataset for Explainable Interpersonal Risk Factors of Mental Disturbance in Social Media PostsMuskan Garg, Amirmohammad Shahbandegan, Amrit Chadha, Vijay MagoACL Findings 2023 · 17 citations
- Legal Judgment Prediction: A Reflection on the State of the ArtYi Feng, Chuanyi Li, Vincent NgACL 2026
