Trained RPDNN LOO-CV models for early rumor detection

This is the release of our RPDNN trained LOO-CV model for early rumor detection.<br>Dataset *_full.zip contains our trained RPDNN models that is developed to predict social media rumor in early stage.<br>The purpose of this release is for research only and for reproducing our results in the paper.<br>For how to load and use the model, please our Allennlp and Pytorch based source code via https://github.com/jerrygaoLondon/RPDNN<br>For more details, please read our paper:<br>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.<br>

本资源发布了我们针对早期谣言检测任务、采用留一交叉验证（Leave-One-Out Cross Validation，LOO-CV）训练得到的RPDNN模型。
数据集*_full.zip 中收录了我们为实现社交媒体早期谣言预测所开发的训练完成的RPDNN模型。
本次发布仅用于学术研究，以及复现论文中的实验结果。
若需了解模型的加载与使用方法，请访问我们基于Allennlp与PyTorch开发的源代码仓库，链接为：https://github.com/jerrygaoLondon/RPDNN
如需了解更多细节，请参阅我们的学术论文：
Gao J、Han S、Song X、Ciravegna F.（2020）.《RP-DNN：基于推文级传播上下文的深度神经网络用于社交媒体早期谣言检测》，收录于《LREC 2020会议论文集》：2020年5月11日至16日在法国马赛举办的国际语言资源与评估大会（International Conference on Language Resources and Evaluation，LREC），LREC 2020。