The problem HateShield solves

In today's digital age, the internet has become a central hub for communication but one of the major drawbacks of online platforms is the proliferation of profanity and offensive language in comments sections.
The prevalence of such language not only degrades the quality of online discourse but also has a profound negative impact on users' experiences and mental well-being.
Exposure to profanity and offensive content can lead to feelings of discomfort, anxiety, and even trauma, especially among sensitive individuals and minors, which many even lead to suicides.
14.9 per cent of teenagers have experienced online bullying, and 13.6 per cent of teenagers have attempted suicide seriously
The people we cater to are concerned parents with underage children surfing the internet, content creators who get hate speeches continuously in their comments leading to extreme unrequired hate, sensitive people who like reading comments but do not wish to read such profane comments
What we provide is : Protecting Mental Well-being: detrimental impact on individuals' mental well-being, causing feelings of distress, anxiety, and discomfort.
Enhancing User Experience: By filtering out profanity and offensive language from online comments, the Profanity Comment Blocker extension aims to improve the overall user experience on social media platform
Empowering Users: Providing users with the ability to filter out profanity and offensive comments empowers them to take control of their online experience

Challenges we ran into

finding NLP datasets with profane and defaming sentences and words in hindi
scrapping comments off youtube and other platforms to do real time analysis
time restriction while integration of multiple models with the extension and training the models