Welcome! This project focuses on detecting emotions from text and identifying whether the text contains hate speech or violent language.
I developed three different RoBERTa-based models to handle these tasks, using a pre-trained tokenizer for efficient processing and the Adam optimizer to improve training precision.
Emotion Detection: Classify the emotional tone of text.
Hate Speech and Violence Detection: Identify potentially harmful or violent language.
antiviolence.py: A standalone script you can run to test the model on your own text inputs.
Install the necessary libraries:
pip install -r requirements.txt Explore the Jupyter Notebook to review the training and evaluation process.
Run antiviolence.py after setting up your environment to test the models yourself!
Feel free to explore, provide feedback, or extend the models further. I’d love to see what you come up with!