Facebook Uses Machine Learning To Spot Suicidal Users
Facebook Uses Machine Learning To Spot Suicidal Users:- This week Facebook announced that it has deployed AI-driven technology to identify users at risk of suicide, and offer them support.
Algorithms, trained on report data from the network’s close to two billion users, are constantly on the lookout for warning signs in content that users post, as well as replies that are received. When a red flag is raised, a team of human reviewers is alerted, and the user can be contacted and offered help.
Facebook has said that it is also working with charities and helplines to develop methods for putting those at risk instantly in contact with a counsellor or advisor.
The social network began monitoring and offering support around suicidal behavior over ten years ago, but until now has relied on its user base flagging up potentially dangerous situations. This marks the first involvement of AI (or machine learning) in the process. The company’s blog post announcing the changes does not go into many specifics, but does give a few clues about how this will be done.
Pattern recognition technology will be used to identify text posts which are “very likely to include thoughts of suicide” and mark them for human intervention. Additionally, or alternatively, it can ensure that others who see them are made aware of their own ability to flag them as indicative of danger of “suicide or self-harm”.
According to Facebook this is the first time that it has deployed AI algorithms to review users’ posts for troubling content – potential future uses include identifying possible terrorists.
The suicide prevention measures have been rolled out into the Facebook Live video streaming service too – following a number of tragic incidents in which users have taken their own lives while broadcasting via the site.
Although it does not mention if or how the measures are assisted by AI in the case of video, users are being given a greater range of options for reporting or reaching out when they think someone is in danger. When a video stream is reported, both the broadcaster and the person who raised the report are offered assistance and links to relevant support resources.
Source:- https://www.forbes.com/sites/bernardmarr/2017/03/02/facebook-uses-machine-learning-to-spot-suicidal-users/#7005e8a33b2b
