/FakeNewsNet-analysis-with-Graph-Classification

Primary LanguageJupyter Notebook

Graph Classification - with hpnf in hpnf folder

Data folder is not included - can be downloaded from https://github.com/mdepak/fake-news-propagation/tree/master/data OR can be crawled from FakeNewsNet api
To use this dataset, un-zip the file nx_network_data.zip file in data directory and one can useload_dataset.py to load the dataset.
To extract features and run the model, install the dependencies in requirements.txt and use basic_model.py's main functio(get_classificaton_results_tpnf).

Graph classification with with unit feature array is in root folder

Data folder is not included - can be downloaded from https://github.com/mdepak/fake-news-propagation/tree/master/data OR can be crawled from FakeNewsNet api
utils/utils.py - utility
load_dataset.py - dataload main file
dgl-gnn-fakenews-gcn-politifact.ipynb
dgl-gnn-fakenews-gcn-gossipcop.ipynb
dgl-gnn-fakenews-gin-politifact.ipynb
dgl-gnn-fakenews-gin-gossipcop.ipynb

Graph classification with profile feature in directory graph_class_with_features

Data folder is not included - can be downloaded from https://codeocean.com/capsule/7305473/tree/v1
data_loader.py - dataload main file
GCN-with-features-gossipcop.ipynb
GCN-with-features-politifact.ipynb