Need help with Amazon-Product-Recommender-System?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

mandeep147
170 Stars 110 Forks 9 Commits 0 Opened issues

Description

Sentiment analysis on Amazon Review Dataset available at http://snap.stanford.edu/data/web-Amazon.html

Services available

!
?

Need anything else?

Contributors list

No Data

Amazon-Product-Recommender-System

Performed sentiment analysis on Amazon Review Dataset available at http://snap.stanford.edu/data/web-Amazon.html

Online shopping is all over the internet. All our needs are just a click away. The biggest online shopping website is Amazon. Amazon is known not only for its variety of products but also for its strong recommendation system.

In our project we are taking into consideration the amazon review dataset for Clothes, shoes and jewelleries and Beauty products. We are considering the reviews and ratings given by the user to different products as well as his/her reviews about his/her experience with the product(s).

Based on these input factors, sentiment analysis is performed on predicting the helpfulness of the reviews. Moreover, we also designed item-based collaborative filtering model based on k-Nearest Neighbors to find the 2 most similar items.

Convert json to CSV using following commands

dataframe = pd.read_json('reviews.json')
dataframe.to_csv('reviews.csv', sep=',', index=False)

Algorithms performed

Sentiment analysis:

  1. Logistic Regression
  2. Naive Bayes - Multinomial and Bernoulli
  3. LSTM

Recommender system:

k-Nearest Neighbors is used to perform item-based collaborative filtering

Contibutions

  1. Sowmya Dharanipragada - Feature Engineering, Support Vector Machines (SVM), Logistic Regression, Rating and upvote prediction
  2. Anushree Sinha - Feature Engineering, K means clustering, Sentiment Intensity Analyzer, LSTM
  3. Mandeep Kaur - Feature Engineering, Naive Bayes - Multinomial, Naive Bayes - Bernoulli, Logistic Regression, and Recommendation system

References:

  1. J. McAuley and J. Leskovec. Hidden factors and hidden topics: understanding rating dimensions with review text. RecSys, 2013.
  2. http://jmcauley.ucsd.edu/data/amazon/
  3. https://www.kaggle.com/snap/amazon-fine-food-reviews

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.