"Detect toxic content to improve online conversations"
In this project, I have implemented both traditional Machine Learning (Multinomial Naive Bayes and Logistic Regression) and Deep Learning Models (Bidirectional LSTM and Bidirectional GRU) with and without pre trained embeddings. The final model is an ensemble of four different models. The dataset is available at https://www.kaggle.com/c/quora-insincere-questions-classification/overview.