× close
Left: I usage according to depression severity (measured by PHQ-9). I usage increases linearly with depression. Right: I usage by participant race after interaction. Among White participants, higher levels of depression increased I use, whereas Black participants' I use levels did not vary with depression severity.
When the researchers used a standard language-based computer model to analyze Facebook posts, they were able to predict the severity of depression in white people, but not in black people. Words and phrases associated with depression, such as first-person pronouns and negative emotion words, predicted depression severity about three times more for whites than for blacks.
This research today Proceedings of the National Academy of Sciencesis co-authored by researchers at the University of Pennsylvania in Philadelphia and the National Institute on Drug Abuse (NIDA), part of the National Institutes of Health (NIH).
Previous research has shown that the language of social media can provide useful information as part of mental health assessments, but the results of this study show that the language used by depressed patients By highlighting key demographic differences, we point out potential limitations in generalizing the language of social media. The results also highlight the importance of including diverse data pools to ensure accuracy in the development of machine learning models, which are applications of artificial intelligence (AI) language models.
“As society seeks to leverage AI and other technologies to provide much-needed mental health care, no one is left out or misrepresented,” said NIDA Director Nora Volkow, MD. We have to make sure that doesn't happen.” She said, “More diverse datasets are essential to ensure that health care disparities are not perpetuated by AI, and these new technologies can help customize more effective medical interventions.”
The study recruited 868 consenting participants who identified themselves as Black or White, and found that a model trained on the Facebook language used by White participants with self-reported depression was When tested on people, it was demonstrated that it showed strong predictive performance. However, when the same model was trained on her Facebook language from Black participants, it performed poorly when tested on Black participants and only marginally better when tested on White participants.
Among White participants, depression severity was associated with increased use of first-person singular pronouns (“me,” “me,” “me”), but this correlation was not found among Black participants. I couldn't see it. Additionally, white people have a strong sense of belonging (“weird,” “creepy”), self-criticism (“messed up,” “terrible”), insecurity and being an outsider (“scared,” “misunderstood,” etc.). self-deprecation (“worthless,” “worthless”) and hopelessness (“begging,” “hollow”) increased with increasing severity of depression, but no such correlation was observed among blacks. There was no relationship. Clinicians have noticed demographic differences in how people express symptoms of depression for decades, but this study explores how this plays out on social media. is shown.
Language-based models show promise as personalized, scalable, and affordable tools for screening mental health disorders. For example, excessive self-referential language, such as the use of first-person pronouns, and negative emotions, such as self-deprecating language, are often considered clinical indicators of depression.
However, racial and ethnic considerations are severely lacking when assessing mental disorders through language, leading to inaccurate computer models. Despite evidence showing that demographic factors influence the language people use, previous research has not investigated how race and ethnicity affect the relationship between depression and verbal expression. We did not systematically investigate whether to give.
Researchers launched this study to fill this gap. They examined the past history of blacks and whites who self-reported their depression severity through the Patient Health Questionnaire (PHQ-9), a standard self-report tool used by clinicians to screen for possible depression. analyzed Facebook posts. Participants agreed to share their Facebook status updates. Participants were primarily female (76%) and ranged in age from her 18 years to her 72 years. The researchers matched the black and white participants for age and gender so that the data from the two groups were comparable.
The findings challenge assumptions about the association between the use of certain words and depression, particularly among Black participants. Current clinical practices in mental health that do not consider racial and ethnic nuances may be less relevant or irrelevant to populations who have historically been excluded from mental health research. the researchers point out. They also hypothesize that depression may not be verbally expressed in the same way in some Black people. For example, in this population, tone and rate of speaking, rather than word choice, are more likely to be associated with depression.
“Our research represents a step forward in building more inclusive language models.To make technology fair for everyone, we need to ensure everyone’s voice is included in AI models. ,” said Brenda Curtis, Ph.D., MSc, Director of Technology and Translational Research. She is a unit in the Translational Addiction Medicine Division of NIDA's Intramural Research Program and is one of the senior authors of this study. “By paying attention to racial nuances in how mental health is expressed, health care professionals can better understand when individuals need help and create more individualized interventions.” We will be able to provide you with
Future research should examine differences between other races and demographic characteristics using different social media platforms, the authors say. They also caution that social media language is not similar to everyday language, so future work on language-based models should take this into account.
“It is important to note that social media language and language-based AI models cannot diagnose mental health disorders and cannot replace psychologists or therapists, but they can be used to screen for personalized interventions. “We have great expectations that this will help provide information,” he said. The study's lead author, Dr. Sunny Lai, is a postdoctoral fellow in computer and information science at the University of Pennsylvania. “Many improvements are needed to integrate AI into research and clinical practice, and the use of diverse and representative data is one of the most important.”
For more information:
Sunny Lai et al., Main linguistic markers of depression in social media depend on race. Proceedings of the National Academy of Sciences (2024). DOI: 10.1073/pnas.2319837121
Magazine information:
Proceedings of the National Academy of Sciences