UK CHARITY Samaritans has teamed up with Twitter to launch an application that warns users if their friends are at risk of suicide.
The Samaritans Radar web app monitors people's tweets and alerts their friends if it spots signs that someone may be struggling to cope. It provides a second chance to see potentially worrying tweets, which might otherwise have been missed.
Developed using Twitter's API, Samaritans Radar uses a special algorithm that searches for specific keywords and phrases in a tweet. The kind of language that would prompt an alert includes explicit phrases such as 'kill myself', 'want to die', or 'end it all'.
If the app sees anything of concern, it sends an email alert with a link to the tweet it has detected, and offers guidance on the best way to provide support to the person who posted the message.
The app is targeted predominantly at the 15 to 35 age group, and will flag potentially worrying tweets from anyone the user is following, including celebrity tweeters.
Joe Ferns, executive director of policy, research and development at Samaritans, said: "We know that people struggling to cope often go online looking for support, but there is still so much we need to learn about why this happens and how we can make the online environment safer for vulnerable people.
"By not addressing this issue we run the risk of shutting these discussions down and driving them underground.
"Instead we need to use tools such as Samaritans Radar to encourage people to look out for one another online, helping them to reach out and offer support."
Patricia Cartes, Twitter's global head of trust and safety outreach, hailed Samaritans for "experimenting with new ways of supporting people in the digital space".
Samaritans Radar isn't the only potentially life-saving feature to be built using Twitter's API. Twitter Alerts launched in the UK last year, notifying users when there is a national crisis or emergency. µ
And that'll cost you a tenner a month
Watch this space
Hackers could erect man-in-the-middle attacks
Painted into a corner