Toxicity detection

Description:

Developed an AI model to detect toxic or harmful comments online using Natural Language Processing (NLP). The model was trained on a large dataset and utilizes deep learning techniques such as LSTM and BERT to accurately classify comments as toxic or non-toxic. This project helps platforms filter harmful content and protect users.

Skills & Tools: Python, TensorFlow/PyTorch, NLP, Data Preprocessing, Deep Learning

Completion Date: 2025