/amazon-fine-food-reviews

Determine the polarity of amazon fine food reviews using ULMFiT, BERT, XLNet and RoBERTa

Primary LanguageJupyter Notebook

Amazon Fine Food Reviews

Determine the polarity of amazon fine food reviews. This dataset consists of reviews of fine foods from amazon. The data span a period of more than 10 years, including all ~500,000 reviews up to October 2012. Reviews include product and user information, ratings, and a plain text review. It also includes reviews from all other Amazon categories.
Dataset can be downloaded from here.

Models used

  • TFIDF Vectorizer with Logistic Regression.
  • ULMFiT with FastAI
  • LSTM using Pytorch and Torchtext.
  • BERT using TensorFlow and Keras.
  • BERT using Pytorch-Transformers.
  • XLNet using Pytorch-Transformers.
  • RoBERTa using Pytorch-Transformers.