Identifying Suicide-Related Language in Smartphone Keyboard Entries Among High-Risk Adolescents
Adolescent suicide rates have risen over the past two decades, underscoring the need for improved risk detection strategies. This study leverages passively-collected smartphone data to identify suicide-related language in adolescents’ keyboard usage using natural language processing (NLP). We developed a suicide lexicon for adolescent language and validated it with labeled data (N=121,515 text entries), demonstrating higher performance than lexicons not designed for youth. Across two independent cohorts at elevated suicide risk (Ns=208/211; >6 million text entries), lifetime suicidal thoughts and behaviors (STB) and current suicidal ideation were associated with increased frequency of smartphone suicide-related language. Human coding indicated varied language, including authentic first-person current suicidal ideation (14.5%) and jokes or hyperbole (20.2%). Compared with the lexicon alone, human coding of suicide-related entries, especially first-person language, showed stronger associations with STB history, highlighting the need for approaches to distinguish intent. Findings highlight both potential and limitations of NLP for suicide prevention.
Authors
- Lauren S. Chernick (ORCID: https://orcid.org/0000-0001-7050-0025)
- Samantha Salem
- Stewart A. Shankman (ORCID: https://orcid.org/0000-0002-8097-4483)
- Joan L. Luby (ORCID: https://orcid.org/0000-0001-5352-1721)
- Jaclyn S. Kirshenbaum (ORCID: https://orcid.org/0000-0001-8685-5840)
- Deanna M. Barch (ORCID: https://orcid.org/0000-0003-1693-8506)
- David Brent
- Karla Joyce
- Lilian Y. Li (ORCID: https://orcid.org/0000-0001-7507-3632)
- Giovanna Porta
- Ashley Blanchard (ORCID: https://orcid.org/0000-0002-1109-6373)
- Katherine Durham
- Paul Alexander Bloom (ORCID: https://orcid.org/0000-0003-3970-5721)
- David Pagliaccio (ORCID: https://orcid.org/0000-0002-1214-1965)
- Adela Schwartz
- Koustuv Saha (ORCID: https://orcid.org/0000-0002-8872-2934)
- Jamie Zelazny (ORCID: https://orcid.org/0000-0002-8750-8223)
- Julia Greenblatt
- Nicholas B. Allen (ORCID: https://orcid.org/0000-0002-1086-6639)
- Caroline P. Hoyniak (ORCID: https://orcid.org/0000-0003-4151-0376)
- Randy P. Auerbach (ORCID: https://orcid.org/0000-0003-2319-4744)
- Isaac N. Treves (ORCID: https://orcid.org/0000-0001-7802-6145)
- Peter Dayan (ORCID: https://orcid.org/0000-0003-3476-1839)
- Hanga Galfalvy (ORCID: https://orcid.org/0000-0001-7156-6106)
- Esha Trivedi (ORCID: https://orcid.org/0009-0003-5658-5546)
- Emma Wool (ORCID: https://orcid.org/0009-0003-8555-102X)
- Natalia Parjane
- Soorya Ram Shimgekar (ORCID: https://orcid.org/0000-0002-1110-9699)
- Isabella Nadel
- Hayley Quinones
Institutions
- Washington University in St. Louis (US)
- Massachusetts Institute of Technology (US)
Publication Details
- Published
- 2025-10-04
- DOI
- https://doi.org/10.31234/osf.io/gfa7h_v2
- Primary Topic
- Suicide and Self-Harm Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00