Amazon Product Review Analysis is Deeplearning based website created with django. It takes the all review page link of a product and gave us how much people like that product. It tell us how positive the product is among the reviewer or consumer by learning about the sentiment of all reviews given by the consumers. this approach best because 3 star review of one person for a perticular product may not be same to 3 star review of other person for same product.
To train the Deeplearning model we used 399995 product reviews.
Done some data cleaning .
convert the reviews int corpus.
then use TfidfTransformer.
The goal of using tf-idf instead of the raw frequencies of occurrence of a token in a given document is to scale down the impact of tokens that occur very frequently in a given corpus and that are hence empirically less informative than features that occur in a small fraction of the training corpus.
Website Home Page
Amazon Product Review Analysis Page
Rseult of product review i
