Table 3 Rumor detection results on Twitter16 datasets.

From: Heterogeneous graph convolutional network for rumor detection with multi-level interactive fusion and graph reconstruction

Method

Acc

NR

FR

TR

UR

\({F}_{1}\)

\({F}_{1}\)

\({F}_{1}\)

\({F}_{1}\)

DTC

0.465

0.643

0.393

0.419

0.403

SVM-TS

0.574

0.755

0.420

0.571

0.526

SVM-TK

0.662

0.643

0.623

0.783

0.655

MVAE

0.631

0.540

0.687

0.721

0.578

RvNN

0.737

0.662

0.743

0.835

0.708

PPC

0.863

0.843

0.898

0.820

0.837

GCAN

/

0.759

0.763

0.759

0.908

VAE-GCN

0.868

0.795

0.809

0.947

0.885

BI-GCN

0.880

0.847

0.869

0.937

0.865

GLAN

0.902

0.921

0.869

0.847

0.968

HGATRD

0.924

0.935

0.913

0.947

0.899

MLI-GRA

0.929

0.946

0.911

0.926

0.933

  1. (N: Non-Rumor; F: False Rumor; T: True Rumor; U: Unverified Rumor).