Toxic Comment Classification

The ascent of online poisonousness represents a serious danger to psychological wellness, especially among young people. Oppressive language in computerized spaces establishes a negative climate, requiring pressing preventive measures. This study presents a Multilingual Harmfulness Recognition Framework controlled by cutting edge AI to resolve this issue. Not at all like conventional receptive strategies, the framework proactively predicts and oversees poisonousness continuously. Its essential objective is to upgrade online security and encourage a more strong computerized world. Using Multilingual BERT, the framework really dissects and arranges harmful substance across various dialects. Through thorough information preprocessing, highlight extraction, and model preparation, it guarantees high exactness in identifying unsafe substance. Intended for web- based entertainment and computerized stages, the framework mitigates the effect of hostile language and misuse. Past being a mechanical arrangement, it effectively defends clients from mental damage. At last, this task advances compassion, understanding, and better internet-based communications.