twitter_sample — Twitter sample (2014)
- Description
A sample of the Twitter social network, obtained by D. Kagan, M. Fire and Y. Elovici with a dedicated crawler of the Twitter API, which collected at most 1,000 friends and followers of each crawled profile. Nodes are Twitter accounts and directed edges represent following relationships between them. The network has 5,384,162 nodes and 16,011,444 edges. The year of the crawl is given as 2014 in the text and as 2012 in the dataset table of the cited paper. The upstream data do not document the direction of the edges, nor the crawling order (e.g. breadth-first) or seed profiles.
In the cited paper, the accounts of the network that were suspended by Twitter about one year after the crawl were used as ground truth for anomalous (malicious) accounts. These labels are not included in the network, which has no node or edge properties.
- Tags
- Social Online Unweighted
- Added
- 2020-08-11
- Citation
-
- D. Kagan, M. Fire, and Y. Elovici, "Unsupervised Anomalous Vertices Detection Utilizing Link Prediction Algorithms", Preprint, arXiv:1610.07525 (2017) arXiv:1610.07525
- Upstream URL RuntimeError: a web page instead of twitter.csv.gz (e.g. an error page of the server)
- http://proj.ise.bgu.ac.il/sns/datasets.html
- Networks
-
Tip: hover over a column header for a description.
Column legend
- $\left<k\right>$
- Mean degree
- $\sigma_k$
- Standard deviation of the degrees
- $\lambda_h$
- Largest eigenvalue of the Hashimoto (non-backtracking) matrix
- $\tau$
- Random walk mixing time
- $r$
- Degree assortativity
- $c$
- Global clustering coefficient
- $\oslash$
- (Pseudo-) diameter
- $S$
- Relative size of the largest component
- NPs
- Node properties
- EPs
- Edge properties