Project 8 : Deep Learning Classification on Social Media
This project is my second take on the “Real or Not ? NLP with Disaster Tweets” Kaggle competition, in which we are provided a list of tweets that can either be about a disaster or not. You can find my first attempt here
Last time, I was rather new to data science. I focused heavily on feature engineering and bags of words to put into machine learning models and managed to obtain a decent score of 78% with ensemble models.
Since I am now more familiar with NLP, and especially with word embeddings, as well as with neural networks, I took another shot at this competition and used these more advanced methods to see if I could obtain better scores than last time and see how far I have progressed. I ended up with a significant increase, with an 82% accuracy score
