Skip to content

ethan-x11/Review-Reflector

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

68 Commits
 
 
 
 
 
 

Repository files navigation

Amazon Product Review Sentiment Analysis using RoBERTa

This project presents a comprehensive solution for analyzing customer sentiments from Amazon product reviews leveraging the power of the RoBERTa pre-trained transformer model.

Features

  • Web Scraping: Efficiently fetches data from Amazon product review pages to handle complex website structures and anti-scraping mechanisms.
  • Data Cleaning and Preprocessing: Ensures data quality through null value removal, punctuation elimination, stopword removal, and unwanted data cleaning.
  • Multilingual Support: Translates foreign language reviews into English for a standardized language framework.
  • Sentiment Analysis: Utilizes the RoBERTa pre-trained Transformer to categorize reviews into positive, negative, and neutral sentiments.
  • Data Visualization:
    • Displays Top 10 positive and negative reviews.
    • Generates trend graphs showcasing sentiment scores over time for both positive and negative reviews.
    • Creates WordClouds to highlight the most frequently used positive and negative terms.
  • User-Friendly Website Interface: Enables users to input product URLs and receive detailed sentiment reports, complete with dynamic visualizations.
  • API Integration: Leverages FASTAPI and Uvicorn for seamless API integration, allowing for easy integration into existing systems or applications.

Benefits

  • Scalable and Efficient: Designed to handle large volumes of Amazon product review data efficiently.
  • High Model Accuracy: Achieves high accuracy in sentiment classification using the robust RoBERTa model.
  • Real-time Data Fetching: Provides up-to-the-minute insights into customer sentiments.
  • Comprehensive Data Processing: Covers data fetching, cleaning, preprocessing, sentiment analysis, and visualization in an end-to-end solution.
  • Diverse Tech Stack: Built using a robust and adaptable tech stack including PyTorch, Transformers, FASTAPI, Uvicorn, NextJS, and TailwindCSS.

How to Use

Detailed instructions on setting up and running the project locally will be provided in a future update.

Contributing

We welcome contributions to enhance the project's features and functionality! Please feel free to fork the repository and submit pull requests.

Let's make this Amazon product review sentiment analysis tool even more powerful and insightful!

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •