A group of scientists has recently published a new paper arguing that monitoring the activity that teens and children have on social-networking sites, such as MySpace and Facebook, could lead to a decrease in the number of suicides in this age group. Victoria University School of Information Management Professor Dr. Tiong-Thye Goh and student assistant Yen-Pei Huang say that they have already developed a decision support system that is able to scan social sites, and find key words that teens between the ages of 18 and 25 are posting online on their profiles, or on other people's profiles.

If the poster, or blogger, uses a very high concentration of these key words, the team says, then it could mean that he or she is at a heightened risk of suicide, depression, inflicting injuries to themselves, or even hurting others. “Social networking sites have in recent years become an increasingly popular avenue for young people to express and to share their thoughts, views and emotions,” Goh explains. “When young people are emotionally distressed for instance, instead of the traditional channel of consulting friends, parents or specialists, social networking blogs may provide a channel to share and release their emotions and intentions,” the expert continues.

The next step in their investigation is for the researchers to devise a way of approaching the persons deemed at risk in a soft manner. Psychiatrists know that it can be extremely difficult to talk to people who are in such a state of mind, especially if they are teens. Goh explains, “Our technology picks up words or phrases such as 'depressed,' or 'I don’t want to live any more' or 'I want to kill somebody.' We analyse the database of phrases and rank them according to frequency of use – if certain key words are used a lot it is likely that the particular person may be emotionally depressed.”

The scientist adds that the team could send an online poll to a person suspected of feeling under the weather, with a question such as “How are you?” Response options could be “Good,” “A bit down,” and “Bad – need help.” Goh says that this approach will be tried out on a small group, until its effectiveness is properly assessed. “The option of needing help would link to an appropriate website that provides useful information and links,” the expert adds, quoted by PhysOrg.