PhiTorch Movie Review/Rating (Sentiment Analysis)

COMP9444: Rating System - Predictive Neural Network by Dean Poulos and Leo Carnovale.

Helpful Links

• http://ir.hit.edu.cn/~dytang/paper/ijcai2015/ijcai15.pdf
• https://www.kaggle.com/xhlulu/zomato-predicting-review-scores-with-lstm
• https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1174/reports/2760995.pdf
• https://github.com/lukysummer/Movie-Review-Sentiment-Analysis-LSTM-Pytorch/blob/master/sentiment_analysis_LSTM.py

Todo

• Implement BCELoss function.
• Research custom loss function. -> https://pytorch.org/docs/master/notes/extending.html
• Research RNN network.
• Research different activations for dense layers.
• Research different optimiser parameters.
• Implement analysis of predicted/actual review-ratings.

Introduction

Pytorch program that learns to read product reviews in text format and predict an integer rating from 1 to 5 stars associated with each review.

Getting Started

Run using: python3 hw2main.py