Epinions
This is the trust network from the online social network Epinions. Nodes are
users of Epinions and directed edges represent trust between the users.
Metadata
Statistics
Size  n =  75,879

Volume  m =  508,837

Loop count  l =  0

Wedge count  s =  74,201,120

Claw count  z =  27,111,469,575

Cross count  x =  9,737,182,087,729

Triangle count  t =  1,624,481

Square count  q =  166,635,817

4Tour count  T_{4} =  1,630,702,496

Maximum degree  d_{max} =  3,079

Maximum outdegree  d^{+}_{max} =  1,801

Maximum indegree  d^{−}_{max} =  3,035

Average degree  d =  13.411 8

Fill  p =  8.837 74 × 10^{−5}

Size of LCC  N =  75,877

Size of LSCC  N_{s} =  32,223

Relative size of LSCC  N^{r}_{s} =  0.424 663

Diameter  δ =  15

50Percentile effective diameter  δ_{0.5} =  3.816 09

90Percentile effective diameter  δ_{0.9} =  5.258 77

Median distance  δ_{M} =  4

Mean distance  δ_{m} =  4.400 33

Gini coefficient  G =  0.814 342

Balanced inequality ratio  P =  0.157 292

Outdegree balanced inequality ratio  P_{+} =  0.184 344

Indegree balanced inequality ratio  P_{−} =  0.170 510

Relative edge distribution entropy  H_{er} =  0.845 432

Power law exponent  γ =  2.025 80

Tail power law exponent  γ_{t} =  1.691 00

Degree assortativity  ρ =  −0.040 645 7

Degree assortativity pvalue  p_{ρ} =  0.000 00

In/outdegree correlation  ρ^{±} =  +0.736 595

Clustering coefficient  c =  0.065 678 8

Directed clustering coefficient  c^{±} =  0.090 296 9

Spectral norm  α =  245.999

Operator 2norm  ν =  139.616

Cyclic eigenvalue  π =  106.528

Algebraic connectivity  a =  0.022 466 4

Reciprocity  y =  0.405 226

Nonbipartivity  b_{A} =  0.723 602

Normalized nonbipartivity  b_{N} =  0.016 785 3

Spectral bipartite frustration  b_{K} =  0.000 753 884

Plots
Matrix decompositions plots
Downloads
References
[1]

Jérôme Kunegis.
KONECT – The Koblenz Network Collection.
In Proc. Int. Conf. on World Wide Web Companion, pages
1343–1350, 2013.
[ http ]

[2]

Matthew Richardson, Rakesh Agrawal, and Pedro Domingos.
Trust management for the semantic web.
In Proc. Int. Semant. Web Conf., pages 351–368. 2003.
