Suicidal Ideation Detection: A Review of Machine Learning Methods and Applications

By Shaoxiong Ji, Shirui Pan, Xue Li, Erik Cambria, Guodong Long, Zi-Liang Huang. 2019

228 citations recorded by the source corpus.

Suicide is a critical issue in modern society. Early detection and prevention of suicide attempts should be addressed to save people’s life. Current suicidal ideation detection (SID) methods include clinical methods based on the interaction between social workers or experts and the targeted individuals and machine learning techniques with feature engineering or deep learning for automatic detection based on online social contents. This article is the first survey that comprehensively introduces and discusses the methods from these categories. Domain-specific applications of SID are reviewed according to their data sources, i.e., questionnaires, electronic health records, suicide notes, and online user content. Several specific tasks and data sets are introduced and summarized to facilitate further research. Finally, we summarize the limitations of current work and provide an outlook of further research directions.

Subfields: Applied Psychology, Clinical Psychology, Social Psychology, Natural Language Processing, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Clinical Psychology

In Social Psychology

In Natural Language Processing

In Safety, Robustness & Interpretability

Citations in the corpus

Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling (2021, background): “These are summarized along with machine learning approaches to the task in Ji et al. (2021), who also highlight several current limitations, such as tenuous links between annotations, the ground truth, and the psychology of suicide ideation and risk.”
SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems (2022, background): “These are summarized along with machine learning approaches to the task in Ji et al. (2021), who also highlight several current limitations, such as ten-uous links between annotations, the ground truth, and the psychology of suicide ideation and risk.”
The Hitchhiker’s Guide to Computational Linguistics in Suicide Prevention (2021, methodology): “…research has been directed at the detection of suicide ideation/behaviors (for updated reviews, see Bernert et al., 2020; Burke et al., 2019; Ji et al., 2020) and depression (Giuntini et al., 2020; Guntuku et al., 2017), one of the most dominant risk factors for suicide behaviors and a…”
Natural language processing applied to mental illness detection: a narrative review (2022, background): “Existing reviews introduce mainly the computational methods for mental health illness detection, they mostly focus on speci ﬁ c mental illnesses (suicide 7 – 9 , depression 10 – 12 ), or speci ﬁ c data sources (social media 13 – 15 , non-clinical texts 16 ).”
Suicide Ideation Detection via Social and Temporal User Representations using Hyperbolic Learning (2021, background): “, 2018) have improved suicide ideation detection (Ji et al., 2020) thanks to a more robust semantic context to interpret the tweet in question, however, lacking user-level context, are often unable to ascertain suicide risk (Sisask et al.”
MentalBERT: Publicly Available Pretrained Language Models for Mental Healthcare (2021, methodology): “Many machine learning-based methods have been applied for suicidal ideation detection (Ji et al., 2021).”