Multi Label Toxic Comment Classification using Machine Learning Algorithms

Toxic comments are the found in online forums that rude, offensive, or unfair and usually cause many users to exit conversation. The threat of bullying abuse on internet obstructs free exchange ideas by limiting people’s opposing viewpoints. Most Websites fail successfully facilitate healthy conversations, leading them either restrict disable user entirely. This paper would explore scope categorize into different labels assess toxicity as accurately possible using machine learning algorithms.