Skip to main content

Table 5 Basic characteristics of the Google News word embedding-based similarity networks obtained for various slicing thresholds on cosine similarity among the corresponding vectors

From: Graph-based exploration and clustering analysis of semantic spaces

Only the words that are also in WordNet are considered.
Cosine similarity threshold0.50.550.60.650.7
Number of nodes5818650576393632650914694
Number of edges20332978010853734587822719557
Average degree69.8831.6713.845.92.66
Largest connected component characteristics
Number of nodes571024671729374113631739
Number of edges2032530798363263731628345885
Average degree71.1934.1717.9511.056.76
Diameter2127456723
Average distance5.757.8911.4518.098.65
Global clustering coefficient0.430.430.410.390.28
Average local clustering coefficient0.370.360.360.360.32
Degree assortativity0.430.410.400.380.11
Largest clique size245155893714