Something in the way: Musician Kurt Cobain committed suicide at the age of 27 after struggling with depression for years. Picture: SUPPLIED
Something in the way: Musician Kurt Cobain committed suicide at the age of 27 after struggling with depression for years. Picture: SUPPLIED

From the way people move and sleep, to how they interact with people around them, depression changes just about everything. It is even noticeable in the way people speak and express themselves in writing.

Sometimes this "language of depression" can have a powerful effect on others. Just consider the impact of the poetry and lyrics of Sylvia Plath and Kurt Cobain, who killed themselves after suffering from depression.

Scientists have long tried to pin down the exact relationship between depression and language, and technology is helping them get closer to a full picture. A new study, published in Clinical Psychological Science, has unveiled a class of words that can help accurately predict whether someone is suffering from depression.

Traditionally, linguistic analyses in this field have been carried out by researchers reading and taking notes. Nowadays, computerised text analysis methods allow the processing of large data banks in minutes.

This can help spot linguistic features that humans may miss, calculating the percentage prevalence of words and classes of words, lexical diversity, average sentence length, grammatical patterns and many other metrics. So far, personal essays and diary entries by depressed people have been useful, as has the work of well-known artists such as Cobain and Plath.

For the spoken word, snippets of natural language of people with depression have also provided insight. Taken together, the findings from such research reveal clear and consistent differences in language between those with and without symptoms of depression.

Language can be separated into two components: content and style. The content relates to what is expressed, the meaning or subject matter of statements.

People with symptoms of depression use an excessive number of words conveying negative emotions, specifically negative adjectives and adverbs such as lonely, sad or miserable. More interesting is the use of pronouns. People with symptoms of depression use more first-person singular pronouns — such as me, myself and I — and fewer second and third person pronouns such as they, them or she. This pattern of pronoun use suggests people with depression are more focused on themselves and less connected with others. Researchers have reported that pronouns are more reliable in identifying depression than negative emotion words.

Rumination (dwelling on personal problems) and social isolation are common features of depression. The style of language relates to how people express themselves, rather than the content we express.

A recent big data text analysis of 64 different online mental health forums, examining more than 6,400 members found that absolutist words, which convey absolute magnitudes or probabilities, such as always, nothing or completely, were better markers for mental health forums than pronouns or negative emotion words.

People with depression will have a more black and white view of the world, and this manifests in their style of language. Compared with 19 different control forums (for example, Mumsnet and Student Room), the prevalence of absolutist words is about 50% greater in anxiety and depression forums, and about 80% greater for suicidal ideation forums.

Pronouns produced a similar distributional pattern as absolutist words across the forums, but the effect was smaller. By contrast, negative emotion words were paradoxically less prevalent in suicidal ideation forums than in anxiety and depression forums.

The research included recovery forums, where members who feel they have recovered from a depressive episode write positive and encouraging posts. Here negative emotion words were used at comparable levels to control forums, while positive emotion words were elevated by about 70%. Nevertheless, the prevalence of absolutist words remained significantly greater than that of controls but slightly lower than in anxiety and depression forums.

Work has begun on using computers to accurately identify increasingly specific subcategories of mental health problems, such as perfectionism, self-esteem problems and social anxiety

People who previously had depressive symptoms are more likely to have them again. Therefore, their greater tendency for absolutist thinking, even when there are no symptoms of depression, is a sign that it may play a role in causing depressive episodes. The same effect is seen in use of pronouns, but not for negative emotion words.

Understanding the language of depression can help to understand the way people with symptoms of depression think, but it also has practical implications. Researchers are combining automated text analysis with machine learning (computers that can learn from experience without being programmed) to classify a variety of mental health conditions from natural language text samples such as blog posts.

Such classification is already outperforming those made by trained therapists. Machine learning classification will improve as more data is provided and more sophisticated algorithms are developed.

This goes beyond looking at the broad patterns of absolutism, negativity and pronouns. Work has begun on using computers to accurately identify increasingly specific subcategories of mental health problems, such as perfectionism, self-esteem problems and social anxiety.

But as the World Health Organisation estimates that more than 300-million people worldwide are now living with depression, an increase of more than 18% since 2005, having more tools available to spot the condition is important to improve health and prevent tragic suicides.

• Al-Mosaiwi is a PhD candidate in psychology a the University of Reading. This article first appeared on The Conversation. 

The Conversation

Please sign in or register to comment.