America is going through a tough phase , the shootouts in School and Colleges have increased manifold in the recent past. In order to combat and make sense of whats been happening, a huge research is being undertaken by the researchers who are currently evaluating 103 teenage students in 74 schools all across the US and ranking them on major or minor behavioral change and aggression towards themselves or others.
An Artificial intelligence system has been developed which can help predict which students are at a higher risk of starting school violence. The Machine Learning Algorithms findings (the science of getting computers to learn over the time without human intervention) are as accurate as any child psychiatrist reports on the similar subject.
Quoting what has been reported in Media – “Previous violent behaviour, impulsivity, school problems and negative attitudes were correlated with risk to others,” said Drew Barzman, a child forensic psychiatrist at Cincinnati Children’s Hospital Medical Center in the US.
“Our risk assessments were focused on predicting any type of physical aggression at school. We did not gather outcome data to assess whether machine learning could actually help prevent school violence. That is our next goal,” said Barzman, lead author of the study published in the journal Psychiatric Quarterly.
The research findings were equally divided between two scales that the research team had developed . The scales were Moderate to high risk and moderate to low risk, and there were major differences in the score between high risk and low risk groups.
The ML algorithms achieved an accuracy of 91.02 per cent when it used interview content to predict risk of school violence, the rate jumped upto 91.45 per cent when more data points like demograhic and socio-economic data were added.
“The machine learning algorithm, based only on the participant’s interview, was almost as accurate in assessing risk levels as a full assessment by our research team, including gathering information from parents and the school, a review of records when available, and scoring on the two scales we developed,” said Yizhao Ni, a computational scientist at Cincinnati. “Our ultimate goal, should research support it, is to spread the use of the machine learning technology to schools in the future to augment structures, professional judgment to more efficiently and effectively prevent school violence,” said Barzman.