Inspiration
Our inspiration stemmed from the need to create a safer and more respectful online environment by effectively detecting and managing toxic language.
What it does
Profanity Police is a comprehensive solution for detecting and managing toxic language in digital communications. It utilizes an advanced profanity checker and a neural network for deeper context analysis to ensure accurate detection.
How we built it
For the profanity filter, we wrote python scripts that created variations from a list of swear words, detected when discord messages were sent, and checked whether they contained a swear word before allowing them to be sent. For the neural network we used the classic model and trained it on the Toxic youtube Comment Dataset. After training, our neural network performs at just under 80% accuracy.
Challenges we ran into
Some challenges we encountered included optimizing the performance of the neural network for real-time analysis and fine-tuning the profanity detection algorithms for accuracy and efficiency.
Accomplishments that we're proud of
We are proud to have developed a powerful tool that can contribute to creating a more positive and respectful online community by effectively combating toxic language.
What we learned
Through building Profanity Police, we gained valuable insights into natural language processing, machine learning, and the importance of addressing ethical considerations in technology development.
What's next for Profanity Police
In the future, we plan to further enhance Profanity Police by incorporating additional features and refine the accuracy of our machine learning model.
Log in or sign up for Devpost to join the conversation.