SentimentAnalysisCNNLSTM

Apply deep learning techniques for sentiment analysis. Quite generally, sentiment analysis combines methods from natural language processing (NLP) and machine learning (ML) or data mining (DM) to understand opinions about a given subject. In the context of this assignment, the sentiment analysis exercise is focused on student opinions about classes they attend. We seek to conduct a polarity classification based on a class session that just ended. Students will be requested to express their opinions about the session using one sentence or a paragraph. Based on an existing model derived from a machine learning method, the opinion will be classified. The overall opinions will then be summarised and presented to the lecturer as feedback. Here, we consider five different classes: 1. excellent 2. very good 3. good 4. average 5. poor The machine learning method used to build the model should be based on deep learning. More specifically, we wish to use a combination of convolutional neural network (CNN) and long short term memory (LSTM).