Feds Financing System to ‘Automatically Detect’ Cyberbullying
Feds Financing System to ‘Automatically Detect’
Cyberbullying
By: Elizabeth Harrington
March 27, 2015 5:00 am
The National Science Foundation (NSF) is financing the
creation of a system for the “automatic detection” of cyberbullying.
The project was awarded this month to Rutgers University,
which has received $117,102 so far. The real-time, automatic detection of
hurtful online speech is necessary, according to the NSF grant, because
cyberbullying is a “critical social problem.” The grant said 40 percent of
American teenagers have reported being cyberbullied.
“This project aims to define new approaches for automatic
detection of cyberbullying by integrating the relevant research in social
sciences and computer science,” the grant said.
The project will involve searching for keywords and
studying the relationships between teenagers who send and receive mean online
messages.
“Specifically, this research will advance the state of
the art in cyberbullying detection beyond textual analysis by also giving due
attention to the social relationships in which these bullying messages are
exchanged,” the grant said.
“A higher accuracy at detection would allow for better
mitigation of the cyberbullying phenomenon and may help improve the lives of
thousands of victims who are cyberbullied each year,” it said.
The project hopes to employ “social intervention
mechanisms” to prevent cyberbullying. Data on cyberbullying will also “be made
available to the larger research community.”
The project begins in July and is set to last through
June 2017.
The goal of the project is to create “better
cyberbullying detectors.”
“By analyzing the social relationship graph between users
and deriving features such as number of friends, network embeddedness, and
relationship centrality, the project will validate (and potentially refine)
multiple theories in social science literature and assimilate those findings to
create better cyberbullying detectors,” the grant said. “The project will yield
new, comprehensive models and algorithms that can be used for cyberbullying
detection in automated settings.”
The grant added that “text mining” of cyber conversations
is not enough, as the project also seeks to conduct data analysis on a “much
bigger scale.”
Vivek K. Singh, Ph.D., an assistant professor in the
School of Communication and Information at Rutgers University, is leading the
project.
“I have worked on multiple projects including designing a
novel media sharing application, detecting patterns in large scale Twitter
feeds, and analyzing community behavior in social media to design mechanisms to
‘nudge’ people into suitable behaviors,” he writes on his website.
Singh previously studied Twitter hashtags, arguing that
people, “make a conscious decision to hash-tag their post, because they want to
relate it to an event which is relevant to others in the same spatio-temporal
volume.”
Singh did not respond to a request for comment.
The Obama administration has placed a priority on
preventing cyberbullying. The Department of Health and Human Services (HHS)
runs a website to stop cyberbullying that encourages Americans to report mean
online behavior to law enforcement and schools.
President Obama and First Lady Michelle Obama hosted the
first ever White House conference on the subject in 2011.
“If there is one goal of this conference, it is to dispel
the myth that bullying is just a harmless rite of passage or an inevitable part
of growing up,” President Obama said.
Other measures to counter cyberbullying have raised
concerns about privacy and government overreach.
A new law in Illinois to combat cyberbullying allows
school administrators to demand the passwords of student’s social media
accounts. Schools only need a “reasonable cause to believe that a student’s
account on a social network contains evidence that a student has violated a
school’s disciplinary rule of policy,” FOX 2 in St. Louis reported.
Australia is seeking to establish an “Office of the
Children’s e-Safety Commissioner,” who can fine social media networks AU$17,000
a day for not taking down a post that the government has deemed cyberbullying.
A bill working its way through the Australian senate defines cyberbullying as
“seriously threatening, seriously intimidating, seriously harassing, or
seriously humiliating.”
Liberal Australian senator Cory Bernardi warned that the
legislation might go too far.
“Ultimately, children need to be taught a bit of
resilience in some ways,” he said. “There is not always going to be someone
there to pick up the hurt feelings.”
Comments
Post a Comment