AI for Safety: Preventing Gang and Gun Violence

AI for Safety: Preventing Gang and Gun Violence

  • The Results
Project finished!

Together with public benefit corporation Voice 4 Impact, 32 collaborators leveraged AI to spot and prevent gang and gun violence. The analysis was done without profiling via analysing tweets and classifying them into threatening and non-threatening tweets.

 

The potential of AI for Safety: Gang and Gun Violence

According to our challenge partner Voice 4 Impact, “Some believe that bolstering school security will deter violence, but this reactionary measure only addresses part of the problem. Instead, we must identify threats, mitigate risk and protect children and staff before an act of violence occurs.”

 

The AI solutions: Spotting and preventing gang and gun violence

First, a tool was created to label tweets faster and train the machine learning model. The sentiment analysis team built a machine learning model to predict whether the tweets are threatening or non-threatening. A community-based network analysis resulted in a directed graph and by using the Girvan Newmann algorithm, the communities in the networks could be also detected. Using PageRank values of each node, the influential members in the network were identified.

 

Where our AI solutions are implemented 

THE INTELLIGENT DATA ECOSYSTEM® (I.D.ECO)

Our AI technology will be integrated into I.D.Eco.

I.D. Eco is the first technology to enable school administrators, law enforcement and public safety officials to proactively monitor and address potential threats before they become acts of violence.

The solution leverages proven marketing technology to interpret the underlying intent of social media posts—from a collective rather than an individual perspective—and provides a window into understanding and predicting threatening behavior. In this way, the AI can spot and prevent gang and gun violence.

We are thanking all community collaborators for the amazing work done! 

 

More information about our friends at

Articles from this project