James Cook University researchers have developed a technique to analyse social media posts to detect early warning signs of mental health distress.
Data scientist Usman Naseem said the method examined historical posts, their timing and the interval between them.
"Social media users tend to express themselves openly and candidly, making it a rich source of data for researchers," he said on Tuesday.
"By distinguishing changes in sentiment, identifying specific language markers and detecting behavioural anomalies, researchers can spot potential risk factors for mental health conditions."
Dr Naseem said the approach effectively captured the context of users' historical posts and irregularities in the time they posted.
"Accurately assessing the state of a user's mind requires understanding the history of the user's mental health condition," he said.
"We comprehensively considered both historical posts and the diverse time intervals between them, so we could gather more accurate and nuanced assessments of a person's mental well-being."
The research team believes the technique could provide mental health professionals and researchers monitoring and supporting vulnerable people with valuable insights.
"Our results demonstrate the new method surpasses current state-of-the-art approaches in mental health surveillance on social media," Dr Naseem said.
"Ideally, we hope this information will become an efficient and effective way for clinicians to provide early intervention and support."
The study was published in the Journal of Social Network Analysis and Mining.
Lifeline 13 11 14
beyondblue 1300 22 4636
18°C