Hierarchical Attention Network for Sentiment Analysis
A PyTorch implementation of the Hierarchical Attention Network for Sentiment Analysis on the Amazon Product Reviews datasets. The system uses the review text and the summary text to classify the reviews as one of positive, negative or neutral. These classes correspond to ratings 4-5, 1-2 and 3 respectively in the dataset.
The code in the repository are organised in following modules:
Following utility scripts have been added for training/testing:
$ ./train.sh <train_data_json>
$ ./test.sh <test_data_json> <result_file>