Trained RPDNN LOO-CV models for early rumor detection
datasetposted on 09.01.2020 by Jie Gao, Sooji Han
Datasets usually provide raw data for analysis. This raw data often comes in spreadsheet form, but can be any collection of data, on which analysis can be performed.
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.
EthicsThere is no human data or any that requires ethical approval
PolicyThe data complies with the funder's policy on access and sharing
Sharing and access restrictionsThe data can be shared openly
- The file formats are open or commonly used
Methodology, headings and units
- Headings and units are explained in the files
- There is a readme.txt file describing the methodology, headings and units