This project uses Recurrent Neural Networks for Sentiment Analysis as a better approach. Its paper can be found in this link We will train a classfier movie reviews in IMDB dataset, using Recurrent Neural Networks.
keras
tensorflow
you can create a conda virtual environment to run the project by using the following command
conda env create -f environment.yml
We will use Recurrent Neural Networks, and in particular LSTMs, to perform sentiment analysis in Keras. Conveniently, Keras has a built-in IMDb movie reviews data set that we can use.
from keras.datasets import imdb
To start training program use this command
python RNNSentiment.py --epochs epochs --batch_size batch_size --vocab_size vocabulary_size --max_words maximum_words --embedding_size embedding_size --lr learning_rate --steps steps_per_epoch
where
- --epochs => no of epochs to train the model
- --batch_size => batch size
- --vocab_size => vocabulary size
- --max_words => the maximum number of words
- --embedding_size => word embedding size
- --lr => learning rate
- --steps => steps per epoch