conda create -n py37_venv python=3.7
conda activate py37_venv
pip install -r requirements.txt
Download data from Google drive.
Please note that data themselves are licensed under Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License. They cannot be redistributed or used for commercial purposes.
mkdir data/
mv data-file-just-downloaded data/SWOW-EN.R100.csv.zip
unzip data/SWOW-EN.R100.csv.zip -d data/
Pre-process the raw data.
python preprocess.py
Run stereotype propagation algorithm. You could specify the GPU device here. Use CPU as default.
python stereotype_propagation.py [--gpu 0]
The stereotype lexicon is at data/stereotype_lexicon.txt
.