Natural Language Processing of Social Media as Screening for Suicide Risk

By Glen A. Coppersmith, Ryan Leary, Patrick Crutchley, Alex B. Fine. Biomedical Informatics Insights, 2018

469 citations recorded by the source corpus.

Suicide is among the 10 most common causes of death, as assessed by the World Health Organization. For every death by suicide, an estimated 138 people’s lives are meaningfully affected, and almost any other statistic around suicide deaths is equally alarming. The pervasiveness of social media—and the near-ubiquity of mobile devices used to access social media networks—offers new types of data for understanding the behavior of those who (attempt to) take their own lives and suggests new possibilities for preventive intervention. We demonstrate the feasibility of using social media data to detect those at risk for suicide. Specifically, we use natural language processing and machine learning (specifically deep learning) techniques to detect quantifiable signals around suicide attempts, and describe designs for an automated system for estimating suicide risk, usable by those without specialized mental health training (eg, a primary care doctor). We also discuss the ethical use of such technology and examine privacy implications. Currently, this technology is only used for intervention for individuals who have “opted in” for the analysis and intervention, but the technology enables scalable screening for suicide risk, potentially identifying many people who are at risk preventively and prior to any engagement with a health care system. This raises a significant cultural question about the trade-off between privacy and prevention—we have potentially life-saving technology that is currently reaching only a fraction of the possible people at risk because of respect for their privacy. Is the current trade-off between privacy and prevention the right one?

Subfields: Applied Psychology, Clinical Psychology, Social Psychology

View Paper: https://www.semanticscholar.org/paper/c8ff66d1b15e2349c53a7c63ec740dc424787d74

How researchers see this paper

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

In Applied Psychology

In Clinical Psychology

In Social Psychology

Citations in the corpus

Suicidal Ideation Detection: A Review of Machine Learning Methods and Applications (2019, background): “Coppersmith et al. [57] developed a deep learning model with GloVe for word embedding, bidirectional LSTM for sequence encoding, and self attention mechanism for capturing the most informative subsequence.”
Artificial Intelligence for Mental Healthcare: Clinical Applications, Barriers, Facilitators, and Artificial Wisdom (2021, background): “Mental illnesses may be observable in online contexts, and social media data have been leveraged to predict diagnoses and relapses (51,72,76,77), with accuracies comparable to clinician assessments and screening surveys (78). f However, sensor data do not yet have clear usability in clinical mental…”
Community-level Research on Suicidality Prediction in a Secure Environment: Overview of the CLPsych 2021 Shared Task (2021, methodology): “We began with data donated to the OurData-Helps.org platform, discussed in greater detail by Coppersmith et al. (2018).”
Suicide Ideation Detection via Social and Temporal User Representations using Hyperbolic Learning (2021, methodology): “, 2019) and LSTMs (Coppersmith et al., 2018) have improved suicide ideation detection (Ji et al.”
The Hitchhiker’s Guide to Computational Linguistics in Suicide Prevention (2021, background): “Alternatively, researchers may collect data from designated sources in which users provide an a priori permission to collect and analyze their data, such as in the recently developed OurDataHelps.org infrastructure (Coppersmith et al., 2018).”
Machine Learning and Natural Language Processing in Mental Health: Systematic Review (2021, unknown): “An exception to this is the group of OurDataHelps.org users [77] who volunteered to participate in scientific research and filled out a questionnaire to provide information about themselves.”
Beyond Screen Time: Identity Development in the Digital Age (2020, methodology): “Based on the combination of natural language processing and deep learning methods trained on retrospective social media data, Coppersmith et al. (2018) were able to accurately identify about 40% of individuals who would go on to attempt suicide (much better predictions than the 4–6% accuracy…”