August 2, 2012
Twitter Helps Researchers Study Factors Of Bullying
Connie K. Ho for redOrbit.com — Your Universe Online
The 2012 Olympics are known as the Twitter Olympics, mostly for the continuous stream of messages by athletes and fans alike. Twitter is not just shaping the landscape of sports, but it´s also shaping the knowledge of bully and victim interactions. In a recent study, researchers utilized microblogging site Twitter to better understand the various factors of bullying.
In the past, scientists have depended on self-reporting surveys to better understand victims and bullies.
"Kids are pretty savvy about keeping bullying outside of adult supervision, and bullying victims are very reluctant to tell adults about it happening to them for a host of reasons," remarked Amy Bellmore, a University of Wisconsin—Madison educational psychology professor, in a prepared statement. "They don't want to look like a tattletale, or they think an adult might not do anything about it."
In the project, Bellmore worked with graduate students Junming Sui and Kwang-Sung Jun as well as computer science professor Jerry Zhu to look for posts on Twitter that mentioned bullying events.
"For a standard study we may get access to students from one grade in one school," explained Bellmore in the statement. "And then we get a one-time shot at it. We get one data collection point in a school year from these kids. It's very labor- and time-intensive."
The team of investigators utilized a computer that monitored Twitter to analyze tweets that had been hand-selected by Bellmore´s research group.
"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," noted Zhu in the statement. "The computers are seeing the aftermath, the discussion of a real-world bullying episode."
On a daily basis, the computer looked at approximately 250 million public posts that appeared on Twitter. The machine quickly began to identify over 15,000 tweets per day that were related to bullying. The researchers saw the traffic of posts on bullying spiked from Monday to Thursday, when students were normally in school.
"The computer gets a set about bullying and a set definitely not about bullying," commented Zhu in the statement. "In machine learning, the algorithm reads each tweet as a short text document, and it goes about analyzing the word usage to find the important words that mark bullying events."
Apart from its ability to look at a bulk amount of messages, the researchers saw that the computer was able to identify the bully versus victim roles taken on by Twitter users.
"We taught it ways to identify bullies, victims, accusers and defenders," explained Bellmore in the statement.
Through the study, the researchers identified a new role of “reporter” who found out about the bullying event but wasn´t directly associated to the situation.
"The other roles were identified in the early '90s in the bullying literature," Bellmore says. "But the reporter role is new. It's just like it sounds, a child who witnessed or found out about, but wasn't participating in, a bullying encounter. That role emerged out of studying the social media roles."
The data pooled from the social media site was particularly helpful in tracking the progression of time, which wasn´t seen before in student surveys; the researchers hope to study more about individual users and their participation in varying bullying experiences.
"Paper surveys are not as dynamic as the social media tracks," commented Zhu in the statement. "You just get one snapshot in time. You don't see the evolution of bullying events. You don't see the relationships evolving."
Based on the findings, the investigators concluded that the computer that tracked social media could be helpful in determining those who need an intervention.
"We want to add sentiment analysis, an assessment of the emotion behind a social media message, to our program," Zhu says. "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. Those are the ones that would need immediate attention."
The researchers also proposed that social media could help victims of bullying feel more comfortable in a community and work through their feelings with one another.
"A way victims often make sense of their bullying is by internalizing it. They decide that there's something bad about themselves – not that these other people are jerks," Bellmore says. "When they're exposed to the idea that other people are bullied, actually it has some benefit. It doesn't completely eliminate the depression or humiliation or embarrassment they might be feeling, but it can decrease it."
Moving forward, the researchers plan to use the study to help government officials better understand bullying issues. They believe that the data could help develop effective prevention techniques. Apart from Twitter, they are also interested in looking at other social media sites like Facebook and China´s Weibo.