Osiris Rankin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Osiris Rankin has a total of 64 co-authors. Here are the top co-authors by number of shared publications:
Daniel D.L. Coppersmith
2 shared publications- John A. Naslund
Department of Global Health and Social Medicine, Harvard Medical School, Boston, MA, United States
2 shared publications Kate Bentley
2 shared publicationsMatthew Nock
Harvard University
2 shared publications- Mauricio J. Núñez-Delgado
Universidad Popular de Cesar, Valledupar, Colombia
2 shared publications Alexander Millner
1 shared publication
Latest Publications
- Open Access
- 29 October 2026
- Published by Elsevier in SSM - Mental Health
- Vol. 10
A social-ecological analysis of psychological self-management among college students
- 29 October 2026
- Published by Elsevier in SSM - Mental Health
- Vol. 10
Open AccessA social-ecological analysis of psychological self-management among college students
- Open Access
- 18 May 2026
- Published by Center for Open Science in PsyArXiv
Using large language models to create lexicons for interpretable text models with high content validity: the Suicide Risk Lexicon
Researchers often want to measure a variety of constructs such as anxiety, discrimination, or loneliness in text data from surveys, interviews, social media, and electronic health records. Using large language models (LLMs) --while optimal for text classification-- remain infeasible for some researchers due to concerns around computational expertise, cost, privacy, and compute requirements. Therefore, some researchers prefer to use lightweight models for large datasets or interpretable models to avoid mistakes in high-stakes scenarios such as suicide risk detection. Lexicons offer simple baselines to LLMs by searching for relevant phrases --and can be used together with LLMs to guarantee capturing specific keywords in a deterministic way. However, building new lexicons is resource intensive. In this study, we found that GPT-4 turbo was able to automatically create a lexicon for 49 known risk factors for suicidal thoughts and behaviors, which we release as the Suicide Risk Lexicon. Generating a lexicon with LLMs quickly measures most constructs relevant for suicide risk detection, resulting in high content validity. This lexicon was able to accurately predict risk in crisis counseling conversations. After validating the lexicon with clinician ratings, the lexicon modestly outperformed the LIWC lexicon --which has low content validity for mental illness-- and performed similarly to some black-box deep learning models. Due to using an interpretable approach with high content validity, we discovered that active suicidal ideation and direct self-injury were stronger indicators of imminent risk than passive suicidal ideation and depressed mood in this ecological setting (i.e., naturalistic counseling conversations as the crisis is happening, as opposed to assessments or interviews about retrospective symptoms). To simplify creating new lexicons for other research domains, we introduce a Python package, construct-tracker, that works with a variety of LLMs. In sum, while we recommend using LLMs for text classification, they remain out of reach for many researchers. Our work demonstrates that LLMs --despite being black-boxes-- can counterintuitively create interpretable models by generating lexicons, when this is preferred. However, more studies are needed to test how these methods generalize to other datasets and psychological domains. Furthermore, we highlight the broader application of lexicons beyond measurement, including their use in benchmarking LLM performance.
- 18 May 2026
- Published by Center for Open Science in PsyArXiv
Open AccessUsing large language models to create lexicons for interpretable text models with high content validity: the Suicide Risk Lexicon
Researchers often want to measure a variety of constructs such as anxiety, discrimination, or loneliness in text data from surveys, interviews, social media, and electronic health records. Using large language models (LLMs) --while optimal for text classification-- remain infeasible for some researchers due to concerns around computational expertise, cost, privacy, and compute requirements. Therefore, some researchers prefer to use lightweight models for large datasets or interpretable models to avoid mistakes in high-stakes scenarios such as suicide risk detection. Lexicons offer simple baselines to LLMs by searching for relevant phrases --and can be used together with LLMs to guarantee capturing specific keywords in a deterministic way. However, building new lexicons is resource intensive. In this study, we found that GPT-4 turbo was able to automatically create a lexicon for 49 known risk factors for suicidal thoughts and behaviors, which we release as the Suicide Risk Lexicon. Generating a lexicon with LLMs quickly measures most constructs relevant for suicide risk detection, resulting in high content validity. This lexicon was able to accurately predict risk in crisis counseling conversations. After validating the lexicon with clinician ratings, the lexicon modestly outperformed the LIWC lexicon --which has low content validity for mental illness-- and performed similarly to some black-box deep learning models. Due to using an interpretable approach with high content validity, we discovered that active suicidal ideation and direct self-injury were stronger indicators of imminent risk than passive suicidal ideation and depressed mood in this ecological setting (i.e., naturalistic counseling conversations as the crisis is happening, as opposed to assessments or interviews about retrospective symptoms). To simplify creating new lexicons for other research domains, we introduce a Python package, construct-tracker, that works with a variety of LLMs. In sum, while we recommend using LLMs for text classification, they remain out of reach for many researchers. Our work demonstrates that LLMs --despite being black-boxes-- can counterintuitively create interpretable models by generating lexicons, when this is preferred. However, more studies are needed to test how these methods generalize to other datasets and psychological domains. Furthermore, we highlight the broader application of lexicons beyond measurement, including their use in benchmarking LLM performance.
- 19 May 2023
- Published by Elsevier in Journal of Behavioral and Cognitive Therapy
- Vol. 33 (2) , 67-80
A qualitative examination of the impact of suicidal thoughts and behavior on help-seeking among university students in Colombia and Mexico
- 19 May 2023
- Published by Elsevier in Journal of Behavioral and Cognitive Therapy
- Vol. 33 (2) , 67-80
A qualitative examination of the impact of suicidal thoughts and behavior on help-seeking among university students in Colombia and Mexico
- Open Access
- 10 May 2023
- Published by Center for Open Science in OSF Preprints
Characterizing suicidal thinking: Examining momentary and daily motivational states, intent and thought content.
Suicide is a leading cause of death. Rich descriptions of suicidal phenomena are critical to advancing understanding. Research on goal-directed behavior suggests that actions require both a motivation and a cognitive representation of the behavior. Therefore, we measured motivational (e.g., desire or urge) and intentional (e.g., intent) suicidal states as well as suicidal thought content (e.g., verbal thoughts, imagery and planning) using momentary (9,786 responses) and daily (2,335 responses) assessment over 42 days in 105 suicidal adults. Results revealed, first that suicidal imagery was more common than verbal suicidal thoughts, and suicide plans co-occurred with imagery approximately 70% of the time. Second, high levels of suicidal desire, urge and intent were frequently accompanied by active suicidal thought content, the reverse was not true: active thought content was frequently present during low or absent motivational/intentional states. These results paint a nuanced and complex picture regarding the phenomenology of suicidal thoughts.
- 10 May 2023
- Published by Center for Open Science in OSF Preprints
Open AccessCharacterizing suicidal thinking: Examining momentary and daily motivational states, intent and thought content.
Suicide is a leading cause of death. Rich descriptions of suicidal phenomena are critical to advancing understanding. Research on goal-directed behavior suggests that actions require both a motivation and a cognitive representation of the behavior. Therefore, we measured motivational (e.g., desire or urge) and intentional (e.g., intent) suicidal states as well as suicidal thought content (e.g., verbal thoughts, imagery and planning) using momentary (9,786 responses) and daily (2,335 responses) assessment over 42 days in 105 suicidal adults. Results revealed, first that suicidal imagery was more common than verbal suicidal thoughts, and suicide plans co-occurred with imagery approximately 70% of the time. Second, high levels of suicidal desire, urge and intent were frequently accompanied by active suicidal thought content, the reverse was not true: active thought content was frequently present during low or absent motivational/intentional states. These results paint a nuanced and complex picture regarding the phenomenology of suicidal thoughts.