enron_priebe — Enron email network of Priebe et al. (1998-2002)
- Description
Directed temporal network of emails among 184 email addresses of the Enron email corpus, as prepared by C. E. Priebe, J. M. Conroy, D. J. Marchette and Y. Park for their study of anomaly detection with scan statistics, in the version distributed by the R package networkDynamicData. The Enron corpus contains about 0.5 million messages from the mailboxes of about 150 Enron employees (mostly senior management, but also energy traders, executive assistants, etc.), which were made public by the US Federal Energy Regulatory Commission during its investigation of the company, and later distributed by William Cohen at Carnegie Mellon University. Priebe et al. obtained 184 unique addresses from the "From" line of the emails in the "Sent" folders, after manually removing addresses clearly not associated with the 150 users. Nodes are these addresses, and each directed edge is an email from the source to the target, with its time; an email to several recipients corresponds to several edges with the same time, and repeated edges between the same pair of addresses correspond to different emails. There are 3,129 distinct ordered pairs of addresses (including 119 self-loops, i.e. emails sent to oneself), and 38,184 email edges. Some of the timestamps are clearly invalid: 53 email edges have the placeholder time 315522000 (1979-12-31), and Priebe et al. restrict their analyses to the 189 weeks from 1998 to 2002; the observation period declared in the data is from 1998-11-13 to 2002-06-21. No email contents are included.
The network has the following properties:
- Nodes:
email_id, the address of the employee without the "@enron.com" part;name, the name of the person associated with the address;role, the role of the person (e.g. "Employee", "Vice President", "Director", "Trader");dept, the department or subsidiary of the person. The names, roles and departments are missing (empty) or redacted for some or many nodes. - Edges:
time, the time of the email, in Unix time (seconds since 1970-01-01);to,cc,bcc, binary flags of the email as given by the source data, without documentation (the large majority of the edges have onlyccset, and nearly all the others have bothtoandbccset, so that the flags may not be encoded as their names suggest);count, an integer given for each email by the source data, also without documentation (possibly the number of copies of the email record in the corpus).
- Nodes:
- Tags
- Social Communication Unweighted Multigraph Timestamps Metadata
- Citation
-
- C. E. Priebe, J. M. Conroy, D. J. Marchette, Y. Park, "Scan Statistics on Enron Graphs." Computational and Mathematical Organization Theory 11(3), 229-247 (2005) 10.1007/s10588-005-5378-z Sci-Hub
- S. Bender-deMoll et al., "networkDynamicData: Dynamic (Longitudinal) Network Datasets." R package (2016) 10.32614/CRAN.package.networkDynamicData Sci-Hub
- Upstream URL OK
- https://cran.r-project.org/package=networkDynamicData
- Upstream license
- CC BY-SA 4.0, https://creativecommons.org/licenses/by-sa/4.0/
- 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