Over a million developers have joined DZone.
{{announcement.body}}
{{announcement.title}}

Using AI To Predict the Risk Of Violence in Schools

DZone's Guide to

Using AI To Predict the Risk Of Violence in Schools

Could this actually work? Read to see whether or not the risk violence in schools can be detected using AI.

· AI Zone ·
Free Resource

Insight for I&O leaders on deploying AIOps platforms to enhance performance monitoring today. Read the Guide.

Bullying is something that most of us have encountered at some point in our lives, but especially whilst at school. It's easy to assume that bullies are all Nelson Muntz style characters and therefore relatively easy to spot, but researchers from Cincinnati Children's Hospital Medical Center believe it's somewhat harder, and indeed that AI can help.

In a recent study, they proved that artificial intelligence can help to predict which students are more likely to perpetrate violence at school. Indeed, the AI-based predictions were so accurate that they were comparable with a team of child and adolescent psychiatrists, including a forensic psychiatrist, in determining risk for school violence.

"Previous violent behavior, impulsivity, school problems and negative attitudes were correlated with risk to others," the authors say. "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."

Spotting Bullies

The algorithm was trained on a cohort of 103 teenage students from across the United States who had a record of major or minor behavioral change and/or aggression towards either themselves or others.

They performed school risk evaluations with each participant, with audio recordings of evaluations transcribed and annotated. The cohort was split roughly equally between high risk and low risk, albeit with a significant difference in the scores between the two groups.

The AI algorithm that the team developed was able to achieve an accuracy rate of just over 91% when using nothing but interview content to predict the risk of school violence, with the accuracy increasing marginally when demographic and socioeconomic data was 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," the team say.

The next step is to explore whether this kind of machine learning based approach can be used in a wide range of schools to augment their existing processes for detecting and preventing school violence.

TrueSight is an AIOps platform, powered by machine learning and analytics, that elevates IT operations to address multi-cloud complexity and the speed of digital transformation.

Topics:
schools ,ai ,machine learning ,bullying ,violence

Published at DZone with permission of

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}