sifatnabil / jigsaw-unintended-bias-in-toxicity-classification Goto Github PK

This was a kaggle competition organized by Jigsaw. The challenge was to build a model that recognizes toxicity in comments and minimizes bias towards the names of frequently attecked identities with toxicity. A labeled dataset was provided for identity mentions. The competition was Kernels-only and here I am showcasing my approach for data processing and designing a model to solve the challenge.

Competition Link

• Numpy
• Pandas
• Seaborn
• NLTK
• Tensorflow

My Local environemnt packages are available in the requirements.txt file.

To install the same packages, run the command:

pip install -r requirements.txt

Name: Sifat Ul Alam
Email: [email protected]
LinkedIn || GitHub || Kaggle

This repository was submitted as a project for Upskill's ISA IM Workshop.