Key language markers of depression on social media depend on race.

Study Author Brenda Curtis

Featured Paper of the Month – September 2024

Published in PNAS with contributions from Salvatore Giorgi and Brenda Curtis of the NIDA IRP Technology and Translational Research Unit.

Summary

Depression correlates with natural language, such as negative emotions and self focus (first person pronouns or “I-usage”). These correlations haven been shown to be robust across several studies. This study shows how race moderates the relationship between language and depression, with I-usage predicting depression in White individuals but not in Black individuals. These results show that psychological processes thought to predict depression may be less relevant in populations historically excluded from psychological research.

Publication Information

Rai, Sunny; Stade, Elizabeth C; Giorgi, Salvatore; Francisco, Ashley; Ungar, Lyle H; Curtis, Brenda; Guntuku, Sharath C

Key language markers of depression on social media depend on race Journal Article

In: Proc Natl Acad Sci U S A, vol. 121, no. 14, pp. e2319837121, 2024, ISSN: 1091-6490.

Abstract | Links

@article{pmid38530887b,

title = {Key language markers of depression on social media depend on race},

author = {Sunny Rai and Elizabeth C Stade and Salvatore Giorgi and Ashley Francisco and Lyle H Ungar and Brenda Curtis and Sharath C Guntuku},

url = {https://pubmed.ncbi.nlm.nih.gov/38530887/},

doi = {10.1073/pnas.2319837121},

issn = {1091-6490},

year  = {2024},

date = {2024-04-01},

urldate = {2024-04-01},

journal = {Proc Natl Acad Sci U S A},

volume = {121},

number = {14},

pages = {e2319837121},

abstract = {Depression has robust natural language correlates and can increasingly be measured in language using predictive models. However, despite evidence that language use varies as a function of individual demographic features (e.g., age, gender), previous work has not systematically examined whether and how depression's association with language varies by race. We examine how race moderates the relationship between language features (i.e., first-person pronouns and negative emotions) from social media posts and self-reported depression, in a matched sample of Black and White English speakers in the United States. Our findings reveal moderating effects of race: While depression severity predicts I-usage in White individuals, it does not in Black individuals. White individuals use more belongingness and self-deprecation-related negative emotions. Machine learning models trained on similar amounts of data to predict depression severity performed poorly when tested on Black individuals, even when they were trained exclusively using the language of Black individuals. In contrast, analogous models tested on White individuals performed relatively well. Our study reveals surprising race-based differences in the expression of depression in natural language and highlights the need to understand these effects better, especially before language-based models for detecting psychological phenomena are integrated into clinical practice.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}