A group of researchers from the University of Colorado Boulder’s CyberSafety Research Center has created an app that can monitor social media accounts for bullying behaviors and send alerts to parents. “BullyAlert” currently works with public Instagram accounts, but the team plans to expand its functions to other platforms in the future. The creators say parents, guardians or other “well-wishers” can sign up for this abuse monitoring system and give feedback on its performance. The app is part of the CyberSafety Research Center’s cyberbullying research initiative.
“All of us need to do better to protect the kids,” study Co-author and Associate Professor in the Department of Computer Science Richard Han said. He added:
The response of the social media networks to fake news has recently started to uptick, even though it took grave consequences to reach that point. The response needs to be just as strong for cyberbullying.
Han and his colleagues used real humans to train their computer programs to differentiate between positive comments like, “Love it!” from negative, abusive ones like, "You suck.” The data-analysis tools can now scan online comments for those that may be offensive or abusive. These posts are then given higher-level secondary checks, while safe-looking posts are moved to the bottom of the queue.
By testing their system on real, publically available data from Vine and Instagram, the team determined their system could detect cyberbullying in real time with 70 percent accuracy. They also created the free BullyAlert Android app -- it will be available for Apple IOS in the fall of 2018. Within the app, parents can give feedback on the accuracy of the alerts they receive, which helps the system personalize its monitoring.
Bullying is defined by the StopBullying.gov page of the U.S. Department of Health and Human Services as “unwanted, aggressive behavior among school aged children that involves a real or perceived power imbalance.” Bullying can have severe negative impacts on the victim and all of those involved, including the perpetrator and bystanders. While suicide can happen for a variety of reasons, it has occurred in direct response to bullying in children as young as eight. Han points out that online harassment is particularly dangerous because it can follow children and young people throughout the day and into their homes.
The CyberSafety Research Center researchers report their anti-bullying tool uses five times less computing resources than similar programs. The program was able to send alert warnings within two hours of posts. This speed of response is not available from other web bully-monitoring apps, according to CU Boulder Today. Examples of apps of the same genre include Auditor, which monitors Gmail for indicators of bullying or the potential intention of self-harm; Net Nanny, which lets parents monitor and filter kids’ online behavior; and STOP!t, which is used within schools and empowers students to report bullying.
“As a parent, I know that a lot of times we are not in full knowledge of what our children are doing on their social networks. An app like this that informs us when something problematic is happening is invaluable,” said Study Co-author and Professor in Computer Science, Shivakant Mishra.
While the BullyAlert system is currently only able to monitor public Instagram accounts, it and similar personal content-monitoring apps may raise some concerns regarding young people’s right to privacy. They also highlight common challenges in communication between generations.
Most social media sites have some version of a requirement that people turn 13 before using them. The Children’s Online Privacy Protection Act, or COPPA, aims to “place parents in control over what information is collected from their young children online.”
Article 16 of the United Nations Convention on the Rights of the Child states, “No child shall be subjected to arbitrary or unlawful interference with his or her privacy, family, home or correspondence, nor to unlawful attacks on his or her honor and reputation.” Finding a balance between respecting young people’s privacy and trying to protect them from abuse is undoubtedly a challenging undertaking.
The CyberSafety Research Center hopes social media networks will use their efficient social media-monitoring methods to make online communities safer.