Truong, Bao Tran
Allen, Oliver Melbourne
Menczer, Filippo
2022-01-31
<p>The dataset includes networks constructed from COVID-related tweets for detecting low-credibility accounts.<br>
We provide three CSV files, corresponding to three networks: the misinformation retweet, the bipartite news-sharing, and the news co-sharing network. All files are tab-separated edge lists; Node labels indicate their credibility: high, low, or unknown (0, 1, and -1 respectively).</p>
<p>An account score is a weighted mean of shared domain scores. Binary labels are provided for sources, rather than scores, to comply with Newsguard licensed usage. The paper uses a threshold of below 60 for low-quality accounts and sources, following Newsguard's convention. However, one can change this threshold depending on the use case. <br>
To apply the LoCred algorithm, the 'rt.csv' file can be used directly. To apply the other PageRank algorithms, the direction of the network needs to be reversed.<br>
The train-test split procedure for evaluation is described in the paper.</p>
<p>More details can be found in our pre-print: https://arxiv.org/abs/2202.00094</p>
https://doi.org/10.5281/zenodo.5932514
oai:zenodo.org:5932514
Zenodo
https://zenodo.org/communities/osome
https://doi.org/10.5281/zenodo.5932513
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
social media
Twitter
covid
low-credibility
misinformation
News Sharing Networks Expose Information Polluters on Social Media
info:eu-repo/semantics/preprint