Wikipedia talk (sk)
This is the communication network of the Slovak Wikipedia. Nodes represent
users, and an edge from user A to user B denotes that user A wrote a message on
the talk page of user B at a certain timestamp.
Metadata
Statistics
Size  n =  41,452

Volume  m =  131,884

Unique edge count  m̿ =  71,933

Loop count  l =  23,137

Wedge count  s =  299,445,255

Claw count  z =  1,426,419,333,688

Cross count  x =  5,768,558,037,351,131

Triangle count  t =  38,859

Square count  q =  55,938,666

4Tour count  T_{4} =  1,645,425,904

Maximum degree  d_{max} =  19,084

Maximum outdegree  d^{+}_{max} =  19,084

Maximum indegree  d^{−}_{max} =  4,191

Average degree  d =  6.363 22

Fill  p =  4.186 37 × 10^{−5}

Average edge multiplicity  m̃ =  1.833 43

Size of LCC  N =  41,076

Size of LSCC  N_{s} =  1,538

Relative size of LSCC  N^{r}_{s} =  0.037 103 2

Diameter  δ =  8

50Percentile effective diameter  δ_{0.5} =  3.061 71

90Percentile effective diameter  δ_{0.9} =  3.814 29

Median distance  δ_{M} =  4

Mean distance  δ_{m} =  3.287 62

Gini coefficient  G =  0.797 885

Balanced inequality ratio  P =  0.179 040

Outdegree balanced inequality ratio  P_{+} =  0.072 821 6

Indegree balanced inequality ratio  P_{−} =  0.261 328

Relative edge distribution entropy  H_{er} =  0.691 012

Power law exponent  γ =  3.865 94

Tail power law exponent  γ_{t} =  1.671 00

Tail power law exponent with p  γ_{3} =  1.671 00

pvalue  p =  0.510 000

Outdegree tail power law exponent with p  γ_{3,o} =  1.621 00

Outdegree pvalue  p_{o} =  0.409 000

Indegree tail power law exponent with p  γ_{3,i} =  2.211 00

Indegree pvalue  p_{i} =  0.955 000

Degree assortativity  ρ =  −0.449 397

Degree assortativity pvalue  p_{ρ} =  0.000 00

In/outdegree correlation  ρ^{±} =  +0.558 059

Clustering coefficient  c =  0.000 389 310

Directed clustering coefficient  c^{±} =  0.019 368 3

Spectral norm  α =  3,635.21

Operator 2norm  ν =  1,825.23

Cyclic eigenvalue  π =  1,803.43

Algebraic connectivity  a =  0.108 020

Spectral separation  λ_{1}[A] / λ_{2}[A] =  1.319 57

Reciprocity  y =  0.086 816 9

Nonbipartivity  b_{A} =  0.939 699

Normalized nonbipartivity  b_{N} =  0.022 163 5

Algebraic nonbipartivity  χ =  0.059 074 1

Spectral bipartite frustration  b_{K} =  0.004 366 08

Controllability  C =  39,153

Relative controllability  C_{r} =  0.944 538

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]

Jun Sun, Jérôme Kunegis, and Steffen Staab.
Predicting user roles in social networks using transfer learning with
feature transformation.
In Proc. ICDM Workshop on Data Min. in Netw., 2016.
