Summarise the distribution of the weights of each measure

Describes the distribution of the weights of each measure: number of edges, mean, standard deviation, extremes, quantiles, and the share of weights equal to zero. (Shen et al. 2019) compare the measures through the shape of their distributions (they report a smooth, right-skewed distribution, well fitted by a lognormal, for the idf-weighted similarity, and more scattered and irregular ones for the other measures except the raw count), which matters when the weights are used by a community detection algorithm or filtered by a threshold. Read the summaries with the scales in mind: a cosine is bounded by 1, the coupling strength is not, so means and quantiles of different measures are not comparable. The ratio_q99_median column, a scale-free indicator of how heavy the right tail is, is.

Usage

summarise_weights(edges, probs = c(0.01, 0.25, 0.5, 0.75, 0.99))

Arguments

edges

A named list of edge tables with a weight column, for instance from compute_couplings().

probs

Numeric vector of probabilities for the quantiles.

Value

A data.table with one row per measure: method, n_edges, mean, sd, min, one column per quantile (q01, q25...), max, share_zero and ratio_q99_median.

Details

References

Shen S, Zhu D, Rousseau R, Su X, Wang D (2019). “A Refined Method for Computing Bibliographic Coupling Strengths.” Journal of Informetrics, 13(2), 605–615. https://linkinghub.elsevier.com/retrieve/pii/S1751157716300244.

See also

Other tools to compare coupling measures: compute_couplings(), correlate_weights(), merge_weights(), overlap_top_weights(), plot_weights()

Examples

library(biblionetwork)
edges <- compute_couplings(Ref_stagflation, "Citing_ItemID_Ref", "ItemID_Ref",
                           weight_threshold = 2)
summarise_weights(edges)
#>        method n_edges        mean         sd          min         q01
#>        <char>   <int>       <num>      <num>        <num>       <num>
#> 1:      angle    1501 0.107669186 0.06044895 0.0207223291 0.030740141
#> 2:   strength    1501 0.009367874 0.01299973 0.0005415795 0.001160528
#> 3: similarity    1501 0.070717811 0.04753687 0.0097282985 0.016752491
#> 4:    jaccard    1501 0.053513766 0.03310502 0.0103092784 0.014925373
#> 5:    vladutz    1501 0.022122321 0.02291125 0.0016339869 0.002849544
#>            q25        q50        q75        q99       max share_zero
#>          <num>      <num>      <num>      <num>     <num>      <num>
#> 1: 0.064051262 0.09274778 0.13483997 0.31250000 0.4291975          0
#> 2: 0.003600744 0.00606473 0.01070624 0.05099059 0.2537136          0
#> 3: 0.038402090 0.05799043 0.08680766 0.24852872 0.3578691          0
#> 4: 0.030612245 0.04444444 0.06756757 0.17647059 0.2692308          0
#> 5: 0.008720930 0.01487280 0.02681704 0.11333333 0.2230769          0
#>    ratio_q99_median
#>               <num>
#> 1:         3.369353
#> 2:         8.407726
#> 3:         4.285685
#> 4:         3.970588
#> 5:         7.620175