Data mining is usually about determining things of economic advantage, but in this case, suicide we have a personal loss and an economic one. A new paper by a group of Japanese researchers, Naoki Masuda, Issei Kurahashi and Hiroko Onari, claims to have found ways of detecting suicidal tendencies — or at least the tendency to think about suicide, so-called "suicide ideation".
The study used the Japanese social network mixi, which has over 27 million members and allows users to join any of over 4.5 million topic groups — some focusing on the subject of suicide. This provided a study and control group to compare. The most interesting finding is that while users in the suicide group had lots of friends they didn't have as many transitive relationships i.e. where A friends B friends C friends A. This suggests that it isn't lack of friends but a lack of tight social groupings that is a factor.
The same technique could be used to investigate similar problems such as depression and alcohol abuse.