FakeNewsDetection

所属分类:内容生成
开发工具:Python
文件大小:29KB
下载次数:0
上传日期:2021-06-18 12:40:58
上 传 者sh-1993
说明:  基于图深度学习的Twitter虚假新闻检测
(Fake News Detection on Twitter using Graph Deep Learning)

文件列表:
CreateData (0, 2021-06-18)
CreateData\CreateSimpleCascade.py (8169, 2021-06-18)
CreateData\collectData.py (8493, 2021-06-18)
CreateData\collectDataNew.py (2023, 2021-06-18)
CreateData\createCascade.py (11714, 2021-06-18)
CreateData\retrieveLostData.py (6299, 2021-06-18)
TrainModel (0, 2021-06-18)
TrainModel\GCN.py (7096, 2021-06-18)
TrainModel\LoadData.py (1556, 2021-06-18)
TrainModel\preprocess.py (7737, 2021-06-18)
convert_data.py (686, 2021-06-18)
dataset_summaries.py (4517, 2021-06-18)
eval.py (14706, 2021-06-18)
feature_extraction_kGNN.py (4529, 2021-06-18)
feature_extraction_kGNN_TopK.py (5178, 2021-06-18)
models.py (3040, 2021-06-18)
train.py (7059, 2021-06-18)

# FakeNewsDetection Fake News Detection on Twitter using Graph Deep Learning Requirements for running the ``CreateDataset`` code: ```shell script conda install python-graphviz pip install searchtweets-v2 pip install TwitterAPI pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.8.1+cpu.html pip install torch-sparse -f https://pytorch-geometric.com/whl/torch-1.8.1+cpu.html pip install torch-cluster -f https://pytorch-geometric.com/whl/torch-1.8.1+cpu.html pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-1.8.1+cpu.html pip install torch-geometric ``` where ```${CUDA}``` and ```${TORCH}``` should be replaced by your specific CUDA version (cpu, cu92, cu101, cu102, cu110, cu111) and PyTorch version (1.4.0, 1.5.0, 1.6.0, 1.7.0, 1.8.0), To create the word embeddings it is required to create a subdir in ``CreateData`` called ``resources``, in this folder you need to place the ``glove.twitter.27B.200d.txt`` file. You can download the file here: https://ndownloader.figshare.com/files/21119193 (original link seems to be broken: https://nlp.stanford.edu/projects/glove/) To create the dataset run the createCascade.py file

近期下载者

相关文件


收藏者