A cluster analysis of scholar and journal bibliometric indicators

We investigate different approaches based on correlation analysis to reduce the complexity of a space of quantitative indicators for the assessment of research performance. The proposed methods group bibliometric indicators into clusters of highly inter-correlated indicators. Each cluster is then associated with a representative indicator. The set of all representatives corresponds to a base of orthogonal metrics capturing independent aspects of research performance and can be exploited to design a composite performance indicator. We apply the devised methodology to isolate orthogonal performance metrics for scholars and journals in the field of computer science and to design a global performance indicator. The methodology is general and can be exploited to design composite indicators that are based on a set of possibly overlapping criteria.

[1]  Dean Hendrix,et al.  An analysis of bibliometric indicators, National Institutes of Health funding, and faculty size at Association of American Medical Colleges medical schools, 1997-2007. , 2008, Journal of the Medical Library Association : JMLA.

[2]  Wolfgang Glänzel,et al.  A Hirsch-type index for journals , 2006, Scientometrics.

[3]  Teofilo F. Gonzalez,et al.  P-Complete Approximation Problems , 1976, J. ACM.

[4]  J. E. Hirsch,et al.  An index to quantify an individual's scientific research output , 2005, Proc. Natl. Acad. Sci. USA.

[5]  L. Egghe,et al.  Theory and practise of the g-index , 2006, Scientometrics.

[6]  Rodrigo Costas,et al.  The h-index: Advantages, limitations and its relation with other bibliometric indicators at the micro level , 2007, J. Informetrics.

[7]  Johan Bollen,et al.  A Principal Component Analysis of 39 Scientific Impact Measures , 2009, PloS one.

[8]  Loet Leydesdorff,et al.  How are new citation-based journal indicators adding to the bibliometric toolbox? , 2009, J. Assoc. Inf. Sci. Technol..

[9]  M. Callon,et al.  From translations to problematic networks: An introduction to co-word analysis , 1983 .

[10]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[11]  Elliotte Rusty Harold,et al.  XML in a Nutshell , 2001 .

[12]  Lutz Bornmann,et al.  Are there better indices for evaluation purposes than the h index? A comparison of nine different variants of the h index using data from biomedicine , 2008, J. Assoc. Inf. Sci. Technol..

[13]  Johan Bollen,et al.  Journal status , 2006, Scientometrics.

[14]  Mônica G. Campiteli,et al.  Is it possible to compare researchers with different scientific interests? , 2006, Scientometrics.

[15]  Henry G. Small,et al.  Co-citation in the scientific literature: A new measure of the relationship between two documents , 1973, J. Am. Soc. Inf. Sci..

[16]  A. Raan.  Measuring Science: Capita Selecta of Current Main Issues , 2004 .

[17]  Yannis Manolopoulos,et al.  Generalized h-index for Disclosing Latent Facts in Citation Networks , 2006, ArXiv.

[18]  M. M. Kessler.  Bibliographic coupling between scientific papers , 1963 .

[19]  Teofilo F. GONZALEZ,et al.  Clustering to Minimize the Maximum Intercluster Distance , 1985, Theor. Comput. Sci..

[20]  Lokman I. Meho,et al.  Impact of data sources on citation counts and rankings of LIS faculty: Web of science versus scopus and google scholar , 2007, J. Assoc. Inf. Sci. Technol..

[21]  Massimo Franceschet,et al.  A comparison of bibliometric indicators for computer science scholars and journals on Web of Science and Google Scholar , 2010, Scientometrics.