Improved author profiling through the use of citation classes

Bart Thijs, Koenraad Debackere, W. Glänzel

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The method of Characteristic Scores and Scales (CSS), previously developed for application at the macro- and meso-level, has been applied to individual author statistics. In particular, two datasets have been used. Firstly, authors with Thomson Reuters Researcher-ID, independently of the field where authors are publishing and, secondly, authors who are active in the field of scientometrics, independently whether they are registered authors or not. The objective is to find a parameter-free solution for citation-impact assessment at this level of aggregation that is insensitive to possible outliers. As in the case of any statistics, the only limitation is the lower bound, which has been set to 10 for the present analysis. The results demonstrate the usefulness of the CSS method at this level while also pointing to some remarkable statistical properties.

Original languageEnglish
Pages (from-to)829-839
Number of pages11
JournalScientometrics
Volume111
Issue number2
DOIs
Publication statusPublished - May 1 2017

Fingerprint

statistics
Statistics
meso level
macro level
aggregation
Macros
Agglomeration

Keywords

  • Characteristic scores and scales
  • Citation classes
  • Evaluatieve bibliometrics

ASJC Scopus subject areas

  • Social Sciences(all)
  • Computer Science Applications
  • Library and Information Sciences
  • Law

Cite this

Improved author profiling through the use of citation classes. / Thijs, Bart; Debackere, Koenraad; Glänzel, W.

In: Scientometrics, Vol. 111, No. 2, 01.05.2017, p. 829-839.

Research output: Contribution to journalArticle

Thijs, Bart ; Debackere, Koenraad ; Glänzel, W. / Improved author profiling through the use of citation classes. In: Scientometrics. 2017 ; Vol. 111, No. 2. pp. 829-839.
@article{3b11c472076048c0ab7696ca3eb5ef1e,
title = "Improved author profiling through the use of citation classes",
abstract = "The method of Characteristic Scores and Scales (CSS), previously developed for application at the macro- and meso-level, has been applied to individual author statistics. In particular, two datasets have been used. Firstly, authors with Thomson Reuters Researcher-ID, independently of the field where authors are publishing and, secondly, authors who are active in the field of scientometrics, independently whether they are registered authors or not. The objective is to find a parameter-free solution for citation-impact assessment at this level of aggregation that is insensitive to possible outliers. As in the case of any statistics, the only limitation is the lower bound, which has been set to 10 for the present analysis. The results demonstrate the usefulness of the CSS method at this level while also pointing to some remarkable statistical properties.",
keywords = "Characteristic scores and scales, Citation classes, Evaluatieve bibliometrics",
author = "Bart Thijs and Koenraad Debackere and W. Gl{\"a}nzel",
year = "2017",
month = "5",
day = "1",
doi = "10.1007/s11192-017-2282-5",
language = "English",
volume = "111",
pages = "829--839",
journal = "Scientometrics",
issn = "0138-9130",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Improved author profiling through the use of citation classes

AU - Thijs, Bart

AU - Debackere, Koenraad

AU - Glänzel, W.

PY - 2017/5/1

Y1 - 2017/5/1

N2 - The method of Characteristic Scores and Scales (CSS), previously developed for application at the macro- and meso-level, has been applied to individual author statistics. In particular, two datasets have been used. Firstly, authors with Thomson Reuters Researcher-ID, independently of the field where authors are publishing and, secondly, authors who are active in the field of scientometrics, independently whether they are registered authors or not. The objective is to find a parameter-free solution for citation-impact assessment at this level of aggregation that is insensitive to possible outliers. As in the case of any statistics, the only limitation is the lower bound, which has been set to 10 for the present analysis. The results demonstrate the usefulness of the CSS method at this level while also pointing to some remarkable statistical properties.

AB - The method of Characteristic Scores and Scales (CSS), previously developed for application at the macro- and meso-level, has been applied to individual author statistics. In particular, two datasets have been used. Firstly, authors with Thomson Reuters Researcher-ID, independently of the field where authors are publishing and, secondly, authors who are active in the field of scientometrics, independently whether they are registered authors or not. The objective is to find a parameter-free solution for citation-impact assessment at this level of aggregation that is insensitive to possible outliers. As in the case of any statistics, the only limitation is the lower bound, which has been set to 10 for the present analysis. The results demonstrate the usefulness of the CSS method at this level while also pointing to some remarkable statistical properties.

KW - Characteristic scores and scales

KW - Citation classes

KW - Evaluatieve bibliometrics

UR - http://www.scopus.com/inward/record.url?scp=85012225038&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85012225038&partnerID=8YFLogxK

U2 - 10.1007/s11192-017-2282-5

DO - 10.1007/s11192-017-2282-5

M3 - Article

AN - SCOPUS:85012225038

VL - 111

SP - 829

EP - 839

JO - Scientometrics

JF - Scientometrics

SN - 0138-9130

IS - 2

ER -