Software detects depressed bloggers

We’re a sunny bunch here at TechEye. It’s partly the gleaming offices and enlightened management, but it’s probably got more to do with the white powder the news editor pours in the water cooler every morning.

But other online writers are not so lucky. Many bloggers sit on their own every night in darkened bedrooms, weeping gently as the government yet again ignores their inspired advice.

But help is at hand.

Researchers at Ben-Gurion University of the Negev (BGU) have developed a software program that can detect depression in blogs and online texts. It analyses the language used, looking for the signs of despair – words like ‘darkness’, ‘alone’ and ‘down’.

The system could potentially be used to screen for would-be suicides, says its developer, associate professor Yair Neuman.

The software was used to scan more than 300,000 English language blogs, and was asked to pick out the most-depressed and least-depressed 100. Its opinion was endorsed in 78 percent of cases by a panel of four clinican psychologists.

It took us a few days to track down Professor Neuman. He agreed to talk to us on condition that he was allowed to remain under the blankets.

“The software program was designed to find depressive content hidden in language that did not mention the obvious terms like ‘depression’ or suicide,’ explained the softly weeping professor.

“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.'”

The next step is to bolt on a little application that automatically emails depressed bloggers and tells them to pull themselves together.