Using large language models to create lexicons for interpretable text models with high content validity: The suicide risk lexicon.

Daniel M Low¹, Osiris Rankin², Daniel D L Coppersmith³, Kate H Bentley⁴, Matthew K Nock², Satrajit S Ghosh⁵

¹DAIR Center, Child Mind Institute.

²Department of Psychology, Harvard University.

³Department of Psychological and Brain Sciences, University of Massachusetts Amherst.

⁴Spring Health.

⁵MIT McGovern Institute for Brain Research.

PubMed DOI

Abstract

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)-although optimal for text classification-remain infeasible for some researchers due to concerns around computational expertise, cost, privacy, and compute requirements. Therefo…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.