T

Tagonizer 2.0

AI-Powered Review, Tag and User Image Correction/Classification Tool

T

Tagonizer 2.0

AI-Powered Review, Tag and User Image Correction/Classification Tool

The problem Tagonizer 2.0 solves

Everyone Loves Online Shopping๐Ÿ›’. But when it comes to selecting a product, we are dependent on the true reviews and actual images of the product put up by past users.
On famous E-Commerce websites like Amazon, Flipkart, AJio, Myntra etc, these reviews, tags and user Images can be misleading, incorrect, paid or simply useless๐Ÿ˜• .

The Main Problem can be concluded in the following points :

  • Useless or Meaningless Auto-Generated Tags ๐Ÿท๏ธ
  • Reviews not classified as positive๐Ÿ‘ or negative ๐Ÿ‘Ž
  • Tags not classified as positive๐Ÿ‘ or negative ๐Ÿ‘Ž
  • Repeated Tags ๐Ÿท๏ธ๐Ÿค”
  • Paid Review Tags that don't reflect sentiments of Customers ๐Ÿ˜ข
  • Misleading Images that don't match the actual product โ“
  • New Buyer or Potential customer had to go through hundreds of reviews, tags and images to judge the product properly ๐Ÿ˜ณ

How Can Users Use our Extension

  • Just install the extension and visit any product on Amazon.in
  • Open up the Tagonizer Chrome Extension, and Voila!
  • Use Tags, Reviews and Images feature to judge a product properly and buy it if you like it
  • Tagonizer, can save you more than 10 min/product at no cost. ๐Ÿ˜ƒ

Updates from Tagonizer 1.0

  • Better Extension UI and errors that caused terrible failing and breaking of Chrome Extension were removed
  • Lags in the Extension were removed, which made the site load faster and more efficiently
  • Dark Mode was added
  • Support for Checking and showing up useful images
  • New Model for NLP and Image Categorization
  • Better Server Strength
  • Extensive Testing on various genres of products
  • Much better server strength
  • We have extensively tested with multiple staging server and staging infra before getting this finally up.

Challenges we ran into

Challenges ๐Ÿ‹๏ธ and Hurdles๐Ÿšง are the most important part of any journey, they make us strong by continuously testing our enthusiasm and patience. We too faced many Challenges, while developing Tagonizer Extension, some of them are:

  • _Code Collaboration_๐Ÿค : Since we are in the middle of a Pandemic, It was hard to collaborate in-person to discuss ideas and develop, hence we had to use tools like Google Meet, Discord, GitHub, UseTogether etc
  • _Errors and Bugs_๐Ÿ› : The Destiny of Every Developer ever, Error and Bugs are our constant companion, and we love to eradicate them, thanks to Stackoverflow, the trustworthy friend
  • Huge Data to Test ๐Ÿ“Š : We had the entire Amazon website, in front of us and the challenge was to efficiently fetch the customer reviews, without affecting the site/ extension performance
  • Efficient UI/UX ๐Ÿ–ฅ๏ธ : Users are our 1st Priority, every bit of attention is paid to the UI of the extension, which was a real challenge to achieve
  • _Production Errors_โš ๏ธ: Production Testing is always different than local testing, we too, faced such issues and the last-minute Debugging was really intense
  • _Breaking Bad_๐Ÿ’ฅ: In Production too, our Extension and Backend API broke a few times, due to load, end sequences or unseen bugs, but all of them were corrected.

Contribution of Each Contributor

  • Himanshu Garg : Responsible for Backend Data Engineering, Backend API, Chrome Extension, Production Testing and Debugging
  • Sonali Singh : Responsible for Front End and Chrome Extension
  • Ankur : Responsible for Deep Learning, Microsoft Azure Cognitive Python SDK Development and Backend Data Engineering

System Design Implementation

System Design Implementation

Discussion