Sentimental Analysis using Long Short Term Memory (LSTM) Neural Network and Inverse Document Frequency Word Embedding Technique

Nowadays, there are so many platforms which allow users to write the reviews and share the comments. Reviews can be related to any product or a service. Users are free to share their feedback and experiences by writing the reviews. As the user count is increasing day by day on a very large scale which results in a drastic increase in the number of reviews. A user can write a positive or negative review according to his or her experience and to classify these reviews manually is the biggest challenge due to a very large amount of data. So, this paper proposes a model which is using deep learning techniques with inverse document frequency word embedding and LSTM (Long Short Term Memory) technique is used to train our model which helps in predicting the sentiment analysis of a review given by any user. Various studies use many machine learning and deep learning techniques to classify the reviews according to their sentiments. Our model is giving accuracy better than the present state of art model.