MADISON (WKOW) -- Researchers at the University of Wisconsin-Madison say they've developed a program to detect evidence of bullying on Twitter.
The program apparently uses an algorithm to scour through the hundreds of millions of tweets sent each day to find words that "mark bullying events." Researchers found kids tend to talk about these events on twitter.
"What we found, very importantly, was that quite often the victim and the bully and even bystanders talk about a real-world bullying incident on social media," Zhu says. "The computers are seeing the aftermath, the discussion of a real-world bullying episode."
The university says the method identifies more than 15,000 bullying-related tweets every day. "We taught it ways to identify bullies, victims, accusers and defenders," says Amy Bellmore, a UW-Madison educational psychology professor.
To learn more about the method, click here.
All content © Copyright 2000 - 2013 WorldNow and WKOW. All Rights Reserved.
Persons with disabilities who need assistance with issues relating to the content of this station's public inspection file should contact Program Manager Jessica Miller at 608-661-2794. Questions or concerns relating to the accessibility of the FCC's online public file system should be directed to the FCC at 888-225-5322, at 888-835-5322 (TTY) or at firstname.lastname@example.org.