Does Artificial Intelligence Recognize Suicidal Tendencies in Social Networks?

//Does Artificial Intelligence Recognize Suicidal Tendencies in Social Networks?

The Government of Canada launches a project together with the Artificial Intelligence company Advanced Symbolics to predict the likelihood of regional suicidal ideation. And, they are not the only ones.

The test project wants to find out which regions of Canada are particularly in need of assistance. It starts in January 2018 and is divided into two phases.

The first one defines what suicide-related behavior in social networks actually looks like. In the second phase, the posts of a representative selection of 160,000 users are checked. It is only about public postings, the privacy of users should not be touched.

Advanced Symbolics also emphasizes not focusing on individual cases, but instead identifying trends. In Canada, suicide is the second preeminent cause of death among the 10 to 19-year-old group. Based on the monitoring data, the company is aiming to make predictions about regional increases in suicidal tendencies.

With this knowledge, the government wants to ensure that areas with high risk can be better assisted. The Artificial Intelligence draws its knowledge not only from the postings examined but also from past incidents, as its director Brenton White tells CBC.

On Cape Breton Island about three teenagers were killed in the past year, in Saskatchewan authorities reported six Suicides within a month. Among other things, the AI uses such information to identify areas of danger at an early stage.

Other companies are working to help people at risk of suicide. In November, Facebook began the rollout of a suicide prevention tool. This allows people at risk to either directly report, or other users can also post from people who point to a risk of suicide.

On Instagram, which is a part of Facebook, users have been able to report videos since last year that might indicate suicide risk.

By |2018-01-17T15:06:59+00:00January 17th, 2018|Technology|1 Comment

One Comment

  1. Omwancha Daniel January 18, 2018 at 8:54 pm - Reply

    Indeed suicide is a very unpredictable event that catches most of us by surprise. It is commendable how digital technology is being deployed to help solve this challenge. This is software to save lives. This is not new, Facebook has already tried to roll out such an AI system. Facebook’s new “proactive detection” artificial intelligence technology will scan all posts for patterns of suicidal thoughts, and when necessary send mental health resources to the user at risk or their friends, or contact local first-responders. Although this human element should not be overlooked, research suggests AI can be a useful tool in identifying mental health problems. One recent study used machine learning to predict whether or not individuals would attempt suicide within the next two years with an 80 to 90 percent accuracy. However, the research only examined data from people who had been admitted to a hospital after self-harming, and wide-scale studies on individuals more representative of the general population are yet to be published. But, with suicide leading to 800,000 deaths worldwide every year, this is a public health issue that cannot be ignored. Given that most humans, including doctors, are pretty terrible at identifying suicide risk, machine learning could provide an important solution.

Leave A Comment