Implementation of AI-Based Social Media for Vulgar Content Detector and Remover

• Published in: International Journal of Advanced Research in Science, Communication and Technology pp. 30 - 34
• Main Authors: Prof. Aarti Burghate, Poonam Bramhane, Pranjal Kuhikar, Pranjali Kanhekar, Ruchika Parate, Anjali Dongre
• Format: Journal Article
• Language: English
• Published: 02.02.2023
• ISSN: 2581-9429; 2581-9429
• DOI: 10.48175/IJARSCT-8066

Social media is a web-based technology that makes it easier for a lot of people to communicate socially. Social media is used by billions of people worldwide to connect and share information. In this project, a social media network powered by AI will be developed for the purpose of identifying and eliminating offensive information. The platform uses machine learning and natural language processing to examine user-generated content and flag any posts or comments that employ offensive language or imagery. The technology is trained using both feedback from human moderators and a dataset of previously detected foul content. Additionally, the site has tools that users can use to report and remove inappropriate information. There are also systems in place to punish or ban individuals who frequently flout community rules. The platform also has a function for automatically detecting and removing vulgar content in real time utilizing language model and picture recognition technologies. By eliminating offensive information and encouraging constructive conversations, this project seeks to build a secure and welcoming online community for its members.