Edinburgh Associative Thesaurus
This is the Edinburgh Associative Thesaurus. Nodes are English words, and a
directed link from A to B denotes that the word B was given as a response to
the stimulus word A in user experiments. Multiple links are allowed, and the
multiplicity of an edge denotes the number of times a word has been given as a
response to another word. In some case, the given word itself was given as a
response, leading to loops in the network.
Metadata
Statistics
Size  n =  23,132

Volume  m =  511,764

Unique edge count  m̿ =  312,310

Loop count  l =  710

Wedge count  s =  30,388,904

Claw count  z =  2,967,734,991

Cross count  x =  376,129,003,421

Triangle count  t =  409,174

Square count  q =  16,682,968

4Tour count  T_{4} =  255,613,548

Maximum degree  d_{max} =  1,076

Maximum outdegree  d^{+}_{max} =  78

Maximum indegree  d^{−}_{max} =  1,044

Average degree  d =  44.247 3

Fill  p =  0.000 583 659

Average edge multiplicity  m̃ =  1.638 64

Size of LCC  N =  23,132

Size of LSCC  N_{s} =  7,751

Relative size of LSCC  N^{r}_{s} =  0.335 077

Diameter  δ =  6

50Percentile effective diameter  δ_{0.5} =  2.935 81

90Percentile effective diameter  δ_{0.9} =  3.852 38

Median distance  δ_{M} =  3

Mean distance  δ_{m} =  3.431 44

Gini coefficient  G =  0.696 577

Balanced inequality ratio  P =  0.231 681

Outdegree balanced inequality ratio  P_{+} =  0.437 125

Indegree balanced inequality ratio  P_{−} =  0.198 509

Relative edge distribution entropy  H_{er} =  0.911 566

Power law exponent  γ =  1.469 67

Tail power law exponent  γ_{t} =  3.211 00

Degree assortativity  ρ =  −0.047 673 9

Degree assortativity pvalue  p_{ρ} =  0.000 00

In/outdegree correlation  ρ^{±} =  +0.532 290

Clustering coefficient  c =  0.040 393 8

Spectral norm  α =  189.271

Operator 2norm  ν =  131.648

Cyclic eigenvalue  π =  57.307 7

Algebraic connectivity  a =  0.961 452

Spectral separation  λ_{1}[A] / λ_{2}[A] =  1.526 69

Reciprocity  y =  0.095 674 2

Nonbipartivity  b_{A} =  0.542 479

Normalized nonbipartivity  b_{N} =  0.482 007

Spectral bipartite frustration  b_{K} =  0.007 915 30

Controllability  C =  14,922

Relative controllability  C_{r} =  0.645 080

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]

George R. Kiss, Christine Armstrong, and Robert Milroy.
An associative thesaurus of English and its computer analysis.
The Comput. and Literary Studies, 1973.
