Trained RPDNN LOO-CV models for early rumor detection

This is the release of our RPDNN trained LOO-CV model for early rumor detection.
Dataset *_full.zip contains our trained RPDNN models that is developed to predict social media rumor in early stage.
The purpose of this release is for research only and for reproducing our results in the paper.
For how to load and use the model, please our Allennlp and Pytorch based source code via https://github.com/jerrygaoLondon/RPDNN
For more details, please read our paper:
Gao. J., Han S., Song X., Ciravegna, F. (2020). “RP-DNN: A Tweet level propagation context based deep neural networks for early rumor detection in Social Media”, In: The LREC 2020 Proceedings. The International Conference on Language Resources and Evaluation, 11-16 May 2020, Marseille. LREC 2020.