A Chinese comments corpus Sentiment analysis.
inspired by Kaggle Yelp competition, and reversion it to Chinese datasets.
reqirement: keras, tensorflow or theano, scikit-learn ,numpy and so on.
key point: embedding, cnn,binary-class.
to do list:
- use pretrained word2vec as inputs.
- use pandas to preprocess data faster.
- modify model structure.
- have a try rnn based sentiment analysis.