See Link ‘e.g., Dou et all, 2021’ this paper for details of UPTD dataset:
News Detection system with GCN Convolution layer, with some visualize data this project has reference on this github project: Link GNN-FakeNews you can check it for further details about this project
-
Open file Link gnn.ipynb
-
run all block
-
Open file Link gnn.ipynb
-
In block 4, change appropriate value that want to tunning it
-
or maybe add new hidden layer and change optimism algorithm
- Dou, Y., Shu, K., Xia, C., Yu, P. S., & Sun, L. (2021). User Preference-aware Fake News Detection. Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. https://doi.org/10.1145/3404835.3462990
- Kipf, T., & Welling, M. (2016). Semi-Supervised Classification with Graph Convolutional Networks. ArXiv: Learning. http://export.arxiv.org/pdf/1609.02907