Detecting h-index manipulation through self-citation analysis

Abstract

The h-index has received an enormous attention for being an indicator that measures the quality of researchers and organizations. We investigate to what degree authors can inflate their h-index through strategic self-citations with the help of a simulation. We extended Burrell's publication model with a procedure for placing self-citations, following three different strategies: random self-citation, recent self-citations and h-manipulating self-citations. The results show that authors can considerably inflate their h-index through self-citations. We propose the q-index as an indicator for how strategically an author has placed self-citations, and which serves as a tool to detect possible manipulation of the h-index. The results also show that the best strategy for an high h-index is publishing papers that are highly cited by others. The productivity has also a positive effect on the h-index.

Fig. 1

Citation profile of an example author

Fig. 2

Average citedness of papers from authors of productivity θ = 3, career length T = 20, mean citation rate with ν = 3 and α = 2

Fig. 3

Development of h _p-index over published papers p for an author with θ = 3, career length T = 20, mean citation rate with ν = 3 and α = 2

Fig. 4

Citation profile c _60,i over paper index i of an author in the unfair and in the random condition with θ = 3, career length T = 20, mean citation rate with ν = 3 and α = 2, and for a total number of published papers of p = θ × T = 60

Fig. 5

Unfair citation profile of Fig. 4 with the q-scores on the x axis

Fig. 6

Summed q-score indexes over published paper p, for the unfair, fair and random condition

Fig. 7

Proportion of papers with fewer citations than the h-paper

Fig. 8

Unnormalized q-index p × Q _p over published papers p, for the unfair, fair and random condition

Fig. 9

a h-Index across the productivity θ. b Same, but on a logarithm productivity scale. On this scale, the fair and random citation strategies confirm the straight lines as also observed by Burrell. The unfair strategy, however, clearly deviates from the linear behavior

Fig. 10

h-Index across the career length T

Fig. 11

h-Index across the number of self citation μ

Fig. 12

h-Index across the height of the citation distribution parameter ν

Fig. 13

h-Index and q-scores across the width of the citation distribution parameter α