Stanford neuroscientists: Teen mental health problems can be predicted by speech patterns. Here’s what to watch for
Computer language models, which analyze what children say during stressful events, are better at predicting their future mental health than a panel of experts in the field. That’s the finding from a new study published in Nature Mental Health. Researchers ran recorded audio interviews of more than 200 children—ages 9 to 13 (on average 11 years old)—through four natural language processing models,…
A recent study published in Nature Mental Health suggests that computer language models can predict future mental health issues in teenagers based on their speech patterns during stressful events. Researchers analyzed recorded interviews of over 200 children aged 9 to 13 (average age of 11) as they discussed stressful events in their personal lives.
The results revealed that the models were "very accurate" in predicting whether these children would develop mental health conditions six years later in adolescence. The study's findings indicate that the style of a child's speech, rather than the content, was more predictive of future mental health problems. For instance, "small connector words" like "and," "to," and "but" were more reliable indicators of stress than the actual descriptions of the events.
The language models also demonstrated the potential of linguistic patterns, such as frequent use of first-person pronouns and prepositions, in indicating mental health risks. Lead author Chase Antonacci, a neuroscience doctoral student at Stanford's School of Humanities and Sciences, stated that the study identifies "markers of risk before individuals are diagnosed."
The research utilized interviews from a broader project overseen by senior author Ian Gotlib, which followed young people over several years. The team employed the Traumatic Events Screening Inventory (TESI) to assess topics such as financial insecurity, parental divorce, abuse, and natural disasters. Gotlib emphasized the potential of language-based assessments, suggesting that future research could involve using smartphone recordings of children talking to identify at-risk individuals years before they might develop a disorder.
Written by urgent.news from Fast Company's reporting — not their text. Machine-written — it may contain errors, so check the original before relying on it.
