Sentiment Analysis Using Simplified Long Short-term Memory Recurrent Neural Networks

LSTM or Long Short Term Memory Networks is a specific type of Recurrent Network (RNN) that is very effective in dealing with long sequence data learning long term dependencies. In this work, we perform sentiment on a GOP Debate Twitter dataset. To speed up training and reduce the cost and time, six different parameter reduced slim versions of LSTM model (slim LSTM) are proposed. We evaluate two of these models on the. The performance of these two LSTM models along with the standard LSTM is compared. The effect of Bidirectional LSTM Layers is also studied. The also consists of a study to choose the best architecture, apart from the best set of hyper parameters for different LSTM Models.