This is the code for the paper:

Viegas, Felipe and Canuto, Sérgio and Gomes, Christian and Luiz, Washington and Rosa, Thierson and Ribas, Sabir and Rocha, Leonardo and Gonçalves, Marcos André. CluWords: Exploiting SemanticWord Clustering Representation for Enhanced Topic Modeling.The Twelfth ACM International Conference on Web Search and Data Mining (WSDM ’19)

To run this code, you need to install/download :

• scipy
• numpy
• gensim
• scikit-learn
• FastText (Pre-trained Word Embedding)

Once installed, setup the paths in the startup file :

main.py

To run the code:

python3 main.py

Also, download the 'wiki-news-300d-1M.vec' from fastext and store it in folder 'clu-exp'

• conda create -n cluwords_env pip
• conda activate cluwords_env
• pip install -r requirements.txt

If you find this code useful in your research, please, consider citing our paper:

title={CluWords: Exploiting SemanticWord Clustering Representation for Enhanced Topic Modeling},
author={Viegas, Felipe and Canuto, Sérgio and Gomes, Christian and Luiz, Washington and Rosa, 
Thierson and Ribas, Sabir and Rocha, Leonardo and Gonçalves, Marcos André},
booktitle={The Twelfth ACM International Conference on Web Search and Data Mining (WSDM ’19)},
year={2019},
organization={ACM}
}```