Published Paper Details:

Social mediahasopenedupaplatformforpeopletoexpresstheirviewsandcommunicatewitha larger audience. However, with this freedom of expression comes a darker side. Social media has become a breeding ground for hateful behavior, abusive language, cyber-bullying, and personal attacks. These types of posts can have a significant impact on others, leading to cyber bullying and harassment. Cyber bullying is the reason for the spread of rumors or threatening messages. Harassment, on the other hand, is unwanted behavior that is intended to intimidate or harm someone. The challenge for social media platforms is to identify and moderate abusive content efficiently to ensure user safety and improve online discussions. Automating this process would help us to identify abusive comments and save time, ultimately making social media a safer place for everyone. Our social media applications that use on-device machine learning to restrict abusive or vulnerable content are becoming increasingly popular. Social media platforms such as Twitter, Face book and YouTube are using machine learning technology to help the match ads to users that will be of highest interest to them. In addition, it is helping to identify violent extremism and fake-news. Amnesty International used machine-learning to quantify the scale of abuse against women on Twitte. Outsourcing this work to machine learning can help reduce the risk of suffering from PTSD as a result of repeated exposure to such distressing content. The application is built using Tensor Flow framework, Firebase database and Flutter. The machine learning algorithms are trained to detect abusive or vulnerable content in real-time and restrict the user from posting such content in offline mode. The application designed to work on multiple platforms including Android and iOS. This one discusses the design and implementation of the application along with the challenges faced during development. The results of the project are presented along with future work that can be done to improve the application.