Can computer programs find signs of depression in our speech?
Computerized analysis of brief speech samples revealed that people with depression use more negative words, more past tense, fewer prepositions, and fewer words expressing uncertainty compared to healthy individuals.
Source
Linguistic markers for major depressive disorder: a cross-sectional study using an automated procedure
What they did
The researchers compared 62 Romanian patients diagnosed with major depressive disorder against 43 healthy controls. Each participant recorded a 5-minute spoken narrative about a hobby or something pleasurable, which was transcribed and analyzed using automated Romanian text-analysis software. They measured depression severity using clinical rating scales and evaluated differences in grammar, emotion words, and content themes.
What they found
Depressed participants spoke using more past tense verbs, negative emotion words, anxiety words, auxiliary verbs, conjunctions, and absolute negations. Conversely, they used significantly fewer positive emotion words, prepositions, and tentative terms like 'maybe' or 'perhaps' compared to the control group. They also talked less about leisure activities and more about home and money, while using shorter sentences that required more periods.
The limits
What it doesn't show
Because this was a cross-sectional study, it cannot prove that these specific language patterns cause depression or that depression directly causes them. The study relied on a relatively small sample of 62 patients and 43 controls, and did not track the effects of antidepressant medications, which can significantly alter energy levels and speech patterns. Additionally, since Romanian is a language where pronoun subjects are often dropped, these specific findings regarding pronoun usage might not apply to English speakers.
Key terms
- Major Depressive Disorder (MDD)
- A common mental health disorder characterized by persistent low mood, loss of interest in activities, and cognitive symptoms lasting at least two weeks.
- Linguistic Inquiry and Word Count (LIWC)
- A computerized text-analysis program that counts and classifies words into grammatical, psychological, and thematic categories.
- Montgomery-Asberg Depression Rating Scale (MADRS)
- A ten-item clinician-rated scale used to measure the severity of depressive symptoms and their sensitivity to change.
- Auxiliary Verbs
- Helping verbs (such as 'have' or 'be') used alongside main verbs to express tense, mood, or voice.
- Function Words
- Words that have little lexical meaning but express grammatical relationships, such as prepositions, pronouns, conjunctions, and auxiliary verbs.
Flashcards
Want these cards to stick?
Save the deck to NoteFren and study it with spaced repetition.
Quiz yourself
Which depressive symptom, excluded in the DSM-5, is included in the ICD-11's definition of a depressive episode due to its strong power to discriminate patients with depression from those without?
Common questions
Why didn't this study find an increase in 'I' pronoun usage, which is common in English studies of depression?
Romanian is a Romance language where the subject pronoun (like 'I') is frequently omitted or built directly into the verb ending. Because of this grammatical feature, the computerized analysis could not easily count individual first-person singular pronouns.
How was the speech collected, and did the topic influence the results?
Participants were asked to talk for about five minutes about a hobby or something they enjoyed. Interestingly, even when asked to talk about a positive topic, depressed individuals still used fewer positive words and more negative language than healthy controls.
Could the differences in education and age between the two groups have skewed the results?
The researchers used statistical regression models to control for age, sex, and years of education, showing that the differences in most language patterns were still independently associated with having depression rather than these background factors.
More on Depression