In this Chalk Talk, you'll use a long short-term memory (LSTM) model to predict sentiment from text using Apache MXNET and Gluon, along with GPU instances with the IMDb dataset. LSTM is a recurrent neural network architecture primarily used in natural language processing (NLP). Sentiment analysis is more than classifying text as positive or negative. It’s an important class of problem for deriving meaning from text in a way that humans understand language. Given the right data, this technique can be used to predict political alignment, writing styles, genre, age of writing, etc. Customers could use this for real-world commercial applications such as monitoring social media feeds, customer service, and more.