###File descriptions

- amazon_reviews.csv - 560,804 unique reviews from Amazon Fine Food Reviews, with their associated star ratings and metadata. It is not necessary to use all reviews, or metadata for training. Some reviews will be missing a value in the 'Score' column. That is because, these are the scores you want to predict.

- sampleSubmission.csv - a sample submission file. Kaggle will only evaluate submission files in this exact same format.

###Data fields

- ProductId - unique identifier for the product
- UserId - unique identifier for the user
- HelpfulnessNumerator - number of users who found the review helpful
- HelpfulnessDenominator - number of users who indicated whether they found the review helpful
- Score - rating between 1 and 5
- Time - timestamp for the review
- Summary - brief summary of the review
- Text - text of the review
- Id - a unique identifier associated with a review

Note: Some of the rows of the table may have some of these values missing.

###Dataset Citation
J. McAuley and J. Leskovec. From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews. WWW, 2013