We have worked on a dataset that contains news headlines - which are aimed to be written in a sarcastic manner by the news author. Our object was to build a Natural Language Processing model for predicting whether the headline is sarcastic or not
Each record of dataset consists of two attributes:
1. is_sarcastic: 1 if the record is sarcastic otherwise 0. This is the target variable.
2. headline: this is the headline of the news article
Train_Dataset.csv
Test_Dataset.csv
All the libraries that was used
1. Python>=3.8
2. Numpy>=1.19
3. Pandas>=1.3.5
4. Sklearn>=0.22
How to install all the necessary libraries using pip
pip install -r requirements.txt