TECHNOLOGY FOR CHANGE

Software Can Diagnose Depression in Blogs and Tweets

Rebecca Kutzer-Rice | Date: 08-30-10 | Comments

Israeli scientists have developed an online application that scans social media for signs of depression. The tool could possibly be used to intervene before suicides occur.

Table of Contents:

Software Can Diagnose Depression in Blogs and Tweets
A team of Israeli scientists has recently created a program that detects signs of depression in online media like blogs, Facebook and Twitter. The software could help doctors reach out to depressed individuals before fatal choices are made.

According to the American Foundation for Suicide Prevention, nearly 35,000 Americans die from suicide each year. Hundreds of thousands more attempt to end their lives. Over 75 percent of these people suffer from major depression�an illness that responds positively to treatment once diagnosed. But because many people with depression withdraw from society and do not actively seek therapy, the illness can be difficult to detect.

Scientists used the application, which is funded by Israel's Defense Ministry, to scan more than 300,000 blogs linked to mental health Websites. By analyzing responses to metaphors and questions, the software identified the 100 most and 100 least depressed individuals. Clinical psychologists then analyzed the data and found that the program made accurate diagnoses 78 percent of the time.

(source: Psychology Today)

"The software program was designed to find depressive content hidden in language that did not mention the obvious terms like 'depression or 'suicide,'" Dr. Yair Neuman from Israel's Bar-Ilan University told Israel21c. "A psychologist knows how to spot various emotional states through intuition. Here, we have a program that does this methodically through the innovative use of 'Web intelligence.'"

"I emphasize that the tool cannot substitute for an expert. It can provide a powerful way to screen for depression through blogs and Facebook. It analyzes text�the written language�and it can help us to identify people who are presenting signs of depression," he said.

Next: Software Can Gauge Other Emotions >>