/Rumor-Spreaders-using-GNN-approach-PHEME-dataset-

Primary LanguageJupyter Notebook

This repository is linked to this paper - "Identifying Possible Rumor Spreaders on Twitter: A Weak Supervised Learning Approach ". The paper is accepted at International Joint Conference on Neural Networks (IJCNN) 2021.

Please note that the code is still in a maintenance state.

The main objectives of this paper -

  1. Data Transformation from PHEME rumor tweets to "possible" rumor spreaders.
  2. Classification using Graph Convolutional Network (GCN) approach.

Tools Used: Anaconda Navigator; Packages used: NLTK, Gensim, t-SNE, PCA, tensorflow, NetworkX

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

Please cite this paper:

@article{sharma2020graph,
title={A Graph Neural Network based approach for detecting Suspicious Users on Online Social Media},
author={Sharma, Shakshi and Sharma, Rajesh},
journal={arXiv preprint arXiv:2010.07647},
year={2020}
}