Sentiment Analysis using Deep Learning – A survey

Opinion Mining and Sentiment analysis on textual data are widely carried out. The main aspect is what techniques we use to accentuate the performance of these models. In this paper, we are going to perform multi-class sentiment analysis using Deep Learning models like Long Short Term Memory (LSTM) and C-LSTM on textual data and compare its performance. We also see its results as compared to other Machine Learning models. Performance evaluation technique like parameter tuning using Dropout regularization is carried out to analyze its effect on the accuracy of the model. The models were also trained using three different datasets for observing the results.