RF-GNN: Random Forest Boosted Graph Neural Network for Social Bot Detection

• python == 3.7
• torch == 1.8.1+cu102
• numpy == 1.21.6
• scipy == 1.7.2
• pandas == 1.3.5
• scikit-learn == 1.0.2
• torch-cluster == 1.5.9
• torch-geometric == 2.0.4
• torch-scatter == 2.0.8
• torch-sparse == 0.6.12
• torch-spline-conv == 1.2.1

• dataset: including [MGTAB, Twibot20, Cresci15].
• model: including ['GCN', 'GAT', 'SAGE', 'RGCN', 'SGC'].
• labelrate: parameter for labelrate. (default = 0.1)

e.g.

#run RF-GCN on MGTAB (label rate 0.05)
python RF-GNN.py -dataset MGTAB -model GCN --labelrate 0.05
#run RF-GAR on Twibot-20
python RF-GNN.py -dataset Twibot20 -model GAT -smote True

• dataset: including [MGTAB, Twibot20, Cresci15].
• model: including ['GCN', 'GAT', 'SAGE', 'RGCN', 'SGC'].
• ensemble: including [True, False].
• labelrate: parameter for labelrate. (default = 0.1)

e.g.

#run RF-GCN-E on MGTAB
python GNN.py -dataset MGTAB -model GCN -ensemble True
#run GCN on MGTAB
python GNN.py -dataset Cresci15 -model GCN -ensemble False

For TwiBot-20, please visit the Twibot-20 github repository. For MGTAB please visit the MGTAB github repository. For Cresci-15 please visit the Twibot-20 github repository.

We also offer the processed data set: Cresci-15, MGTAB, Twibot-20.