PELESent is a library for polarity classification using distant supervision. The library is composed of different learning algorithms ranging from traditional machine learning techniques and representations to state-of-the-art deep learning architectures. The library also has a crawler for twitter along with preprocessing methods.
This code has the following dependencies:
- TensorFlow or Theano
- Keras
- NumPy
- Gensim
- Scikit-learn
Please cite 1 if using this code.
[1] Edilson A. Corrêa Jr, Vanessa Q. Marinho, Leandro B. dos Santos, Thales F. C. Bertaglia, Marcos V. Treviso, Henrico B. Brum, PELESent: Cross-domain polarity classification using distant supervision
@article{correa2017pelesent,
title={PELESent: Cross-domain polarity classification using distant supervision},
author={Corr{\^e}a Jr, Edilson A and Marinho, Vanessa Queiroz and Santos, Leandro Borges dos and Bertaglia, Thales F C and Treviso, Marcos V and Brum, Henrico B}},
journal={6th Brazilian Conference on Intelligent Systems (BRACIS)},
year={2017}
}
For more information, you can contact me via edilsonacjr@gmail.com or edilsonacjr@usp.br.
Best, Edilson A. Corrêa Jr.