Final Project as part of NLP2022 course
This repo contains:
- Raw @yairlapid tweets (in
dataset/yairlapid_tweets.csv
). - Cleaned tweets + simple augmentation dataset (
dataset/cleaned_yairlapid_tweets.csv
). - Cleaned tweets + simple augmentation + back-translation dataset (
dataset/cleaned_translated_yairlapid_tweets.csv
). - Augmentation Jupyter Notebook (
YairLapid Tweets Augmentation.ipynb
). - Full paper (
paper/YairLafeed.pdf
)
- Dataset was retrieved from
@yairlapid
twitter's feed, using Twitter API. - Data should be read using Python's
csv
package.
The colab notebook we worked on can be found here.
Raw link if needed:
https://colab.research.google.com/drive/1234vhtAy9fssJGdmzDuNCPr1ZXnQRbWu?usp=sharing
You can simply run the code in Jupyter notebook and Colab.