WOLFRAM

Wolfram Language & System Documentation Center

Statistical Analysis of the Slashdot

Use the Wolfram Language's strong probability and statistical capabilities to analyze the social network emerging from Slashdot, a technology-related news website known for its specific user community.

    
Import the data and build the friend/foe network:
Wolfram Language code: data = Import["http://snap.stanford.edu/data/soc-Slashdot0902.txt.gz", "Table"];
Wolfram Language code: graph = Graph[DirectedEdge@@@data[[5 ;; ]]]; wcc = Subgraph[graph, First[WeaklyConnectedComponents[graph]]]; scc = Subgraph[graph, Last[SortBy[ConnectedComponents[graph], Length]]];
Find the number of nodes and edges:
Wolfram Language code: {VertexCount[graph], EdgeCount[graph]}
Find the number of nodes and edges in largest WCC:
Wolfram Language code: {VertexCount[wcc], EdgeCount[wcc]}
Find the number of nodes and edges in largest SCC:
Wolfram Language code: {VertexCount[scc], EdgeCount[scc]}
Find the average clustering coefficient:
Wolfram Language code: N[MeanClusteringCoefficient[graph]]
Analyze the in-degree distribution:
Wolfram Language code: indegree = VertexInDegree[graph]; lndist = EstimatedDistribution[indegree, LogNormalDistribution[mu, si]]; pdist = EstimatedDistribution[indegree, ParetoDistribution[k, al]]; emdist = EmpiricalDistribution[indegree];
Wolfram Language code: pstyle = Directive[Thick, #]& /@ {Red, Blue, Green}; plots = LogLinearPlot[{CDF[lndist, x], CDF[pdist, x]}//Evaluate, {x, 5, 1500}, PlotStyle -> pstyle[[2 ;; 3]]]; listplot = ListLogLinearPlot[{Table[{x, CDF[emdist, x]}, {x, DistributionDomain[emdist]}]}, PlotStyle -> First@pstyle]; Legended[Show[{plots, listplot}, ImageSize -> 400, Frame -> True], Placed[SwatchLegend[pstyle, {"data", "log-normal", "pareto"}, LegendFunction -> "Frame"], {{.98, .03}, {1, 0}}]]