Communications of the ACM
Learning Machines Scour Twitter in Service of Bullying Research
University of Wisconsin-Madison researchers are developing a computational method for searching through social media posts to find mentions of bullying events.
"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," says Madison professor Jerry Zhu.
The computer analyzed about 250 million publicly visible messages posted on Twitter and found more than 15,000 bullying-related tweets per day. "We taught [the machine-learning algorithm] ways to identify bullies, victims, accusers, and defenders," says Madison professor Amy Bellmore. The technique also could be used to identify children in need of intervention. "The idea is that if someone is powerfully affected by the event, if they are feeling extreme anger or sadness, that's when they could be a danger to themselves or others," Zhu says.
Using the data to show victims that they are not alone also could help children deal with their feelings, according to the researchers. "When they're exposed to the idea that other people are bullied, actually it has some benefit," Bellmore says.
From University of Wisconsin-Madison
View Full Article
Abstracts Copyright © 2012 Information Inc., Bethesda, Maryland, USA
No entries found