The News Pit

Saturday, 19th September 2020

Anti-Cyberbullying App Launched: Uses Artificial Intelligence (AI) to combat social media bullying

By Simi Nath -
  • Updated
  • :
  • 16th July 2020,
  • 2:38 PM

Anti-Cyberbullying App Launched: The app will protect social media users from any kind of possible bullying by monitoring user’s social media profile and scanning offensive incoming as well as offensive outgoing messages.

anti-cyberbullying apps

Anti-Cyberbullying App Launched: Scientists from Aston University, Birmingham, have launched a cyberbullying ‘Shield’ app to control and combat trolling and bullying online. Scientists have used novel artificial intelligence algorithms which are designed to understand written language, analyze messages and offensive content, to build the app. This anti-cyberbullying app, Bullstop was developed by Semiu Salawu, a doctoral researcher in the College of Engineering and Physical Sciences and was initially designed with teenagers aged 13 upwards in mind.

The app will protect social media users from any kind of possible bullying by monitoring user’s social media profile and scanning offensive incoming as well as offensive outgoing messages. Bullstop is the only anti-cyberbullying app that integrates directly to social media platforms to protect users from bullies and trolls messaging them directly. The app is currently in a beta testing stage, researchers are inviting users of the app to provide feedback and allow them to make improvement.

Read More: New York Times editor Bari Weiss resigns after uproar over Tom Cotton op-ed

PhD student Semiu Salawu who designed Bullstop said: “This application differs from other apps because the use of artificial intelligence to detect cyberbullying is unique in itself. Other anti-cyberbullying apps, in comparison, use keywords to detect instances of bullying, inappropriate or threatening language.

“The detection AI has been trained on over 60,000 tweets to recognise not only abusive and offensive language but also the use of subtle means such as sarcasm and exclusion to bully, which are otherwise difficult to detect using keywords.

“It uses a distributed cloud-based architecture that makes it possible for ‘classifiers’ to be swapped in and out. Therefore, as better artificial intelligence algorithms become available, they can be easily integrated to improve the app.”- Salawu adds.

The app has already been tested and approved by the main target audience- young people and professionals including teachers, police officers and psychologists. A psychiatrist who reviewed the app said: “It has a ‘stop and think’ section, which for any child who does not directly want to bully or does not have the intention of bullying, is very positive. Also, I don’t think any child would install an app if they know it allows their parents access, so the decision not to include parental monitoring in the app is the right one”.

A spokesperson for the West Midlands Police cybercrime unit said: “My initial impression was very good. As a user, or even as perhaps a guardian, I can go through the tour of the app and understand very quickly what the application is trying to achieve. I think the fact it does not have a parents’ or companion app should be used a selling point. If someone is being bullied online, I would definitely recommend this app to them and if this tool is publicly available, then I could see it would be something the police could recommend as a safeguarding tool.”

Due to the ongoing global pandemic and lockdown, lives have moved further online which drastically increases the chance of cyberbullying and abuse. This unique invention by scientists of Aston University will definitely help young people and adults to protect themselves from trolling and bullying online.

Leave a Reply

Your email address will not be published. Required fields are marked *