Language sentiment can tell future depression symptoms, says Yale University Study

Research bodies suggested a link between the language a person uses and depression. Those with depression reportedly use more negative emotional words on social media.

Study in US: A new study by Yale University has found that the words a person uses while responding to open-ended questions show if the person is having a major depressive disorder. It is found to be the same with both the large language model ChatGPT and the human evaluators.

The findings of the study were reported in the Proceedings of the National Academy of Sciences on September 16, 2024. An increasing research body suggested that there is a link between the language people use and depression. Depressed people use more negative emotional words.

Robb Rutledge, an assistant professor of psychology in Yale’s Faculty of Arts and Sciences and senior author of the study said, "Analysis of the language people use offers extra information that clinicians currently don’t have, and our approach could be one way clinicians evaluate their patients."

Yale research also explores whether language can tell someone's future symptoms

In this research, the scientists also tried to explore whether the language used by the people can also provide insights into their future symptoms. To understand this, the researchers asked 467 participants to complete 9 neutral short-answer questions which were open-ended and the Patient Health Questionnaire (PHQ-9) to evaluate the severity of depression. After three weeks, the participants completed all the PHQ-9 questionnaires again.

They used a tool called Linguistic Inquiry and Word Count (LIWC) to calculate how many words the responder used in a particular category. The researchers noticed how many words the responders wrote to the short-answer questions which had a negative or positive emotional tone.

“This told us that human raters were picking up on something that just counting emotion words could not,” said Robb Rutledge.

The lab of coauthor Jutta Joormann, the Richard Ely Foundation Professor of Psychology and lead author Jihyun Hur, a Ph.D. student in Rutledge’s lab said in a joint statement, “We wanted to look at word order and the multidimensional aspect of language central to shaping emotional tone. That’s when we got interested in ChatGPT.”

“Analysis of the language people use offers extra information that clinicians currently don’t have, and our approach could be one way clinicians evaluate their patients. You want a combination of tools that work across lots of people, which together can give you a snapshot of an individual. If some of those tools are automated like this, that frees up the clinician to spend more time trying to help the patient," said Rutledge.

Read more:

• Imperial, Tokyo Tech students explore collaborations in health and wellbeing
• Exploration, Hope and Openness Define New President Jonathan Levin: Stanford University