Discussing things you care about can be difficult. The threat of abuse and harassment online means that many people stop expressing themselves and give up on seeking different opinions. Platforms struggle to effectively facilitate conversations, leading many communities to limit or completely shut down user comments. In this project, I to built a multi-headed model that’s capable of detecting different types of of toxicity like threats, obscenity, insults, and identity-based hate better than Perspective’s current models.The dataset I used comprises of comments from Wikipedia’s talk page edits.
Disclaimer: the dataset for this project contains text that may be considered profane, vulgar, or offensive.
Checkout my model in the given link- https://comment-classifier-poushali.herokuapp.com/