This project is part of my Udacity Nanodegree Program. This is Capstone project in which I have performed sentiment analysis on IMDB dataset.
- Imdb.py: This class provides re-usable methods to load dataset and perform some pre-processing task on the reviews.
- naive-bayes.ipynb: Sentiment analysis using Naive Bayes classification.
- rnn-lstm-sentiment.ipynb: Sentiment analysis using RNN/LSTM. ( I support this most )
Before running ipynb files ensure that the appropriate file is placed inside dataset directory. Else, modify the path of dataset in the respective ipynb files.
- Python 3.6+
- Tensorflow 1.7
- Pandas
- Numpy
- Matplotlib
- Scikit-learn
- Nltk
- A Critical Review of Recurrent Neural Networks for Sequence Learning: https://arxiv.org/pdf/1506.00019.pdf
- Understanding LSTM Networks: http://colah.github.io/posts/2015-08-Understanding-LSTMs/
- The Unreasonable Effectiveness of Recurrent Neural Networks: http://karpathy.github.io/2015/05/21/rnn-effectiveness/
- Kaggle Problem Reference: https://www.kaggle.com/c/word2vec-nlp-tutorial#description
- Perform sentiment analysis with LSTMs, using TensorFlow https://www.oreilly.com/learning/perform-sentiment-analysis-with-lstms-using-tensorflow
- Naive bayes: Predicting movie review sentiment https://www.dataquest.io/blog/naive-bayes-tutorial/
- Word2Vec Tutorial - The Skip-Gram Model http://mccormickml.com/2016/04/19/word2vec-tutorial-the-skip-gram-model/