Correlation analysis for comparison of the citation impact of journals, magazines, and conferences in computer science
| DOI | https://doi.org/10.1108/OIR-11-2014-0273 |
| Date | 08 June 2015 |
| Published date | 08 June 2015 |
| Pages | 310-325 |
| Author | Wei-Chao Lin,Chih-Fong Tsai,Shih-Wen Ke |
| Subject Matter | Library & information science,Information behaviour & retrieval |
Correlation analysis for
comparison of the citation impact
of journals, magazines, and
conferences in computer science
Wei-Chao Lin
Department of Computer Science and Information Engineering,
Hwa Hsia University of Technology, Taipei, Taiwan
Chih-Fong Tsai
Department of Information Management,
National Central University, Jhongli, Taiwan, and
Shih-Wen Ke
Department of Information and Computer Engineering,
Chung Yuan Christian University, Jhongli, Taiwan
Abstract
Purpose –In many research areas, there are a variety of different types of academic publications,
including journals, magazines and conferences, which provide outlets for researchers to present
their findings. Generally speaking, although there are differences in the reviewing criteria and
publication processes of different publication types, in the same research area, there is certainly
overlap in terms of the problems addressed and the audience for different publication types. Therefore,
the research impacts of different publication types in the same research area should be moderately
or highly correlated. The paper aims to discuss these issues.
Design/methodology/approach –To prove this hypothesis, the authors examine the correlation
coefficient of citation impacts for different types of publications, in seven research areas of computer
science, from 2000 to 2013. In particular, four related citation statistics are examined for each
publication type, which are average citations per paper, average citations per year, average annual
increase in individual h-index, and h-index.
Findings –The analysis results show only a partial correlation in terms of several specific
citation measures for different publication types in the same research area. Moreover, the level of
correlation of the citation impact between different publication types is different, depending on
the research area.
Originality/value –The contribution of this paper is to investigate whether the research impact of
different types of publications in the same area is correlated. The findings can help guide researchers
and academics choose the most appropriate publication outlets.
Keywords Citation analysis, h-index, Computer science, Conference publications,
Correlation coefficient, Journal publications
Paper type Case study
Introduction
Citation analysis is one of the most popular types of quantisation methods used to
analyse the research impact of research papers. In general it is based on examining the
frequency of citations in papers (Garfield, 1983; Rubin, 2010). In other words a total
is calculated based on the number of citations a paper has received in other
publications. Papers with larger numbers of citations can simply mean that they have a
higher research impact than those with fewer citations in the same subject areas.
Online Information Review
Vol. 39 No. 3, 2015
pp. 310-325
©Emerald Group Publishing Limited
1468-4527
DOI 10.1108/OIR-11-2014-0273
Received 20 November 2014
Second revision approved
18 March 2015
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/1468-4527.htm
310
OIR
39,3
The h-index is an example of one citation analysis method. It has been used to
measure both the productivity and impact of the published work of a scientist
or scholar (Hirsch, 2005) based on the set of their most often cited papers and the
number of citations that they have received in other publications. In other words a
scholar with an index of hmeans that he or she has published hpapers, each of which
has been cited in other papers at least htimes. Therefore the h-index can be used to
measure the number of publications and the number of citations per publication for
each scholar. Similarly it can be used to assess journal quality and impact (Harzing and
van der Wal, 2009; Mingers et al., 2012).
Research publications can be classified into different types, most commonly
journals, magazines and conferences. Many related studies have appeared in the
literature analysing the citation impact of different publication types for specific
research questions. For instance to name just a few, with the goal of identifying centres
of excellence in different fields worldwide Bornmann et al. (2014) analysed journal
papers, reviews and conference papers in the period from 2005 to 2009. Coursaris and
Van Osch (2014) conducted a scientometric analysis of individuals, institutions and
countries in the social media research domain, analysing 610 research papers published
in journals and conference proceedings between 2004 and 2011. Fernandes (2014)
examined the authorship trends in software engineering (SE), including the number
of authors and the number of scientific publications, collecting data from 122
conferences and journals for the period from 1971 to 2012. Liu and Fang (2014) focused
on the authorship preferences of leaders of scientific groups in seven research fields
and 11 geographic locations. They examined publication data collected from the
Thomson Reuters’ISI Web of Science database.
In another study de Winter et al. (2014) conducted a longitudinal analysis of citation
counts for two highly cited papers and 56 papers published in different research fields
with the goal of estimating retroactive and actual growth percentages of the Web of
Science vs Google Scholar. Abramo et al. (2014) aimed to examine whether the most
productive scientists are also the ones that produce the most frequently cited papers.
The number of citations is considered a measure of the productivity of a scientist.
Their analysis is based on Italian academics in the environmental sciences for the
period from 2004 to 2008. They show that there is a moderate correlation between being
a highly productive scientist and the probability of producing highly cited papers .
Didegah and Thelwall (2013) assessed 11 factors associated with higher impact
research in the areas of biology and biochemistry, chemistry and social sciences using
data collected from the Web of Science from 2000 to 2009.
In another work Albarran et al. (2010) compared the scientific performance of the
US and the EU in terms of geographical areas. They analysed ISI index papers
including journal papers, reviews, conference papers and research notes from 1998 to
2007. Liu et al. (2013) presented a new full-text citation analysis method based on topic
modelling and network analysis algorithms in order to enhance classical bibliometric
analysis and related publication rankings. Their collected data included 111 journals
and 1,442 conference proceedings in the field of computer science published between
1951 and 2011. Zhang et al. (2013) proposed a new framework for syntactic and
semantic analysis of citation content. Its aim is to better analyse the rich sociocultural
context of research behaviour. Related publications, such as journal papers, conference
papers, book chapters, reports, etc. can be used in their proposed framework.
Despite the large number of related studies, none have focused on examining the
correlation coefficient of citation impacts between different publication types in
311
Correlation
analysis
To continue reading
Request your trial