NaturalStupidlty / FakeNewsDetection

ai_house_fake_news_detection

Setup Working Environment

Pre-requirements

• conda 4.12.0 (later versions may also work) - Installation
• VS Code - Ubuntu Installation
• (Optional) CUDA Version: 11.4; Driver Version: 470.129.06 - Installation

Setup environment

If you have CUDA

conda env create -f environment_gpu.yaml

Otherwise

conda env create -f environment.yaml

Start Jupyter

You may use any port

jupyter lab --port 7766

Content

• Workshop. Colab
• Week 1 Session 1
• Week 1 Session 2
• Week 2 Session 1
• Week 2 Session 2
• Week 3 Session 1
• Week 3 Session 2

Use Kaggle or Colab for computations

Kaggle

1. Create Kaggle account
2. Create Notebook
3. Explore docs and find out how
   • Add Kaggle dataset to notebook
   • Turn on GPU

Colab

1. Create Notebook in Colab
2. Enable GPU
3. Add Kaggle dataset to Colab - https://www.geeksforgeeks.org/how-to-import-kaggle-datasets-directly-into-google-colab/

Data

• For Week 2 and 3 we will use Kaggle datasets. Prepare in advance
  • Fake and real news dataset API command: kaggle datasets download -d clmentbisaillon/fake-and-real-news-dataset
  • Toxic Comment Classification Challenge API command: kaggle competitions download -c jigsaw-toxic-comment-classification-challenge
  • Our propaganda detection dataset - kaggle datasets download -d vladimirsydor/propaganda-detection-our-data
  • Unsupervised ru propaganda dataset 01-02-2022 till 30-01-2023 - kaggle datasets download -d vladimirsydor/ru-propaganda-2022-year

How to use Kaggle datasets

1. Create Kaggle account
2. Create Kaggle account
3. Proceed with Installation & Authentication
4. Download dataset with API command