Amazon Reviews Sentiment Classification : Project Overview🎯

A machine learning web application to predict whether the given amazon's fine food review is positive or negative.

• A web application to predict whether the given amazon's fine food review is positive or negative using machine learning and NLP.
• Analyzed nearly 500,000 food reviews from Amazon and built a ML model to predict the sentiment.
• Achieved training accuracy of 0.90 & testing accuracy of 0.89

Live app : https://amzn-food-sentiment-classifier.herokuapp.com/

Tools used🛠

• Python 3.7
• Libraries
  • NLTK
  • Scikit-Learn
  • Flask
  • Numpy
• HTML
• Bootstrap

Run this application☢

• Step 1: Download zip file and extract or clone this repository
  git clone https://github.com/ashok49473/sentiment-classifier-amazon-food.git

• Step 2: Open your command promt
  change directory : cd desktop/sentiment-classifier-amazon-food

• Step 3: Install dependencies
  pip install -r requirements.txt

• Step 4: Run the application
  python app.py

• Step 5: Copy the url from the terminal and open it in your favourite browser.

Demo

• Home Page
  
  

• Result