0% found this document useful (0 votes)
25 views13 pages

Some Thoughts On Citations: Do They Matter? Are They Fair? What Can We Do To Increase Our Citations?

Citations matter to editors, administrators making hiring and funding decisions, and award committees. While citations are an imperfect measure of impact, absence of citations can only be interpreted negatively. To increase citations, researchers should conduct solid work in active fields, write clearly for broad audiences, promote their work through talks and collaborations, and consider reworking older pieces or writing reviews to reach new readers.

Uploaded by

Shanavas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
25 views13 pages

Some Thoughts On Citations: Do They Matter? Are They Fair? What Can We Do To Increase Our Citations?

Citations matter to editors, administrators making hiring and funding decisions, and award committees. While citations are an imperfect measure of impact, absence of citations can only be interpreted negatively. To increase citations, researchers should conduct solid work in active fields, write clearly for broad audiences, promote their work through talks and collaborations, and consider reworking older pieces or writing reviews to reach new readers.

Uploaded by

Shanavas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 13

Some Thoughts on Citations:

Do They Matter? Are they


Fair? What Can We Do to
Increase Our Citations?

JYRKI WALLENIUS

Graduate School Seminar in Systems Analysis, Decision


Making and Risk Management 5-7.12.2007
Who cares?

• Citations matter to journal editors


• Rectors, Deans, Department Heads -- colleagues
• Awards Committees (as one piece of information)
• Are they fair? … not necessarily (and hard to compare
across fields) – surrogate measure of impact of research
– “Good” research papers earn citations, but so do
• Review papers
• Polemic papers
• Papers containing mistakes
(Absence of citations can, however, only be interpreted in one
way …)
• Other measures of impact: Success of your students?
Number of first rate publications? Outside research
funding generated? To what extent is your research being
applied?

2
What Citations Are We Talking About?
ISI (Thomson Scientific), Scopus (Elsevier), Google
Scholar (Google) – differences in coverage and time span

• The ISI database covers over 8650 journals: 1955+ for


Science Citation Index Expanded; 1975+ for Arts and
Humanities Citation Index; 1973+ for Social Sciences
Citation Index
• Scopus covers: 15,000 journals (Over 1,000 Open Access
journals, 500 Conference Proceedings, 600 Trade
Publications, 25 Book Series)
– 16 million records going back to 1996
– 17 million pre-1996 records going back as far as 1869
• Google Scholar covers: peer-reviewed papers, theses,
books, abstracts, and other scholarly literature from all broad
areas of research. Works from a wide variety of academic
publishers, universities and professional societies, as well as
scholarly articles available across the web.

3
Focus on ISI – the oldest (existed prior to
the electronic era)

• What information can we find from ISI? We can do all


kinds of searches based on: author names,
keywords, affiliations, years (articles and citations)

– Journal articles
– Citations to a paper, author (numbers as well as
information about the papers actually citing
somebody’s paper)
– Information who cites you
– Basic statistics (about an author, field, sub-field)

4
Bibliometric Analysis of MCDM/MAUT

• We have conducted a bibliometric study of MCDM/ MAUT


using the ISI database. The ISI database covers over 8650
journals. It found 6910 MCDM/ MAUT publications covering
years 1970-2007.
• We report basic statistics regarding how our fields have
developed based on variations of the following key words:
multiple criteria decision, multiattribute utility, multiple
objective programming/optimization, goal programming,
Analytic Hierarchy Process, evolutionary/genetic
multiobjective, and vector optimization
• The # of pubs included in the SCI has roughly doubled from
1992 to 2006 – interesting to compare the growth in
MCDM/MAUT

5
6
7
TABLE 2: Sub-topical Areas

OR and MS 2415 34.9%


Computer science, AI and IS 829 30.4%
Management and business 1587 23.0%
Applied mathematics, interdisc. 1066 15.4%
Environmental 689 10.0%
Industrial engineering 641 9.3%
Manufacturing engineering 405 5.9%
Economics 308 4.5%
Civil Engineering 289 4.2%
Energy and water resources 267 3.9%
8
Sub-topical Areas: changes over the years

• We also compared ISI publication figures for years


1970-1990 and years 2002-2006. Clear shifts are
noticable:
– The relative share of OR/MS and Mgmt & Business
topics has decreased about 40%
– The share of computer science has increased by
some 20%
– The share of environmental ISI MCDM/MAUT
publications has doubled
– All engineering areas (except for IE) have increased
considerably

9
Publication History: Area of Research
500

450

400

350 AHP
Goal Programming
300
EMO
250 MAUT
Math Programming
200
French School
150 Vector Optimization

100

50

0
-1979 1980- 1985- 1990- 1995- 2000-
1984 1989 1994 1999 2004
10
Citation Statistics: MCDM/MAUT

• 7254 publications (By December 4th, 2007)


• Average number of citations 5.89/paper
• Median number of citations 2
• 35% = earned 0 citations
• Best earned 551 citations
• About 25 papers earned 100 or more citations
• What is the life span of an article?
– 10 yrs? 30 yrs? –- normal distribution?? Some papers
might get noticed rather late …

• Note: Have not purged self-citations from the


statistics (excluding self-citations, median = 0?)

11
12 most cited MCDM/MAUT ISI articles --
tentative
1. YAGER RR: On Ordered Weighted Averaging Aggregation …, IEEE TRANSACTIONS ON SMC 18,1988: 551 citations

2. GEOFFRION AM: Proper Efficiency and …, J. OF MATH ANALYSIS AND APPLICATIONS 22, 1968: 424 citations

3. GEOFFRION AM, DYER JS, and A. FEINBERG: An Interactive Approach for Multicriterion …, MANAGEMENT SCIENCE 19,
1972: 337 citations

4. DEB K, PRATAP A, AGARWAL S, et al.: A Fast and Elitist Multiobjective Genetic …, IEEE TRANSACTIONS ON
EVOLUTIONARY COMPUTATION 6, 2002: 320 citations

5. ZITZLER E, THIELE L: Multiobjective Evolutionary Algorithms …, IEEE TRANSACTIONS ON EVOLUTIONARY


COMPUTATION 3, 1999: 317 citations
6. ZIONTS S, WALLENIUS J: Interactive Programming Method … MANAGEMENT SCIENCE 22,1976: 263 citations

7. TORRANCE GW, FEENY DH, FURLONG WJ, et al.: Multiattribute Utility Function for a Comprehensive Health …, MEDICAL
CARE 34: 1996, 263 citations
8. BENAYOUN R. et al: Linear Programming with Multiple ... (STEM), MATH PROGRAMMING 1, 1971: 247 citations

9. ZAHEDI F.: The AHP – A Survey … , INTERFACES 16, 1986: 241 citations

10. EDWARDS W.: How to Use Multiattribute Utility …, IEEE TRANSACTIONS ON SMC 7, 1977: 188 citations
11. DYER JS: Remarks on the AHP Process, MANAGEMENT SCIENCE 36,1990: 187 citations

12. DYER JS, SARIN RK: Measurable Multiattribute Value Functions, OPER. RES. 27, 1979: 167 citations

12
What can we do to improve citations, impact?

• Do solid research – something interesting to say


• Choose an appropriate journal (not Proceedings, not national
outlet) (journal with a relatively high IF; active and growing fields
• Write well (not overly technical) – always seeking a broader
audience (write from a reader’s point of view: whom do you want
to read your papers?)
• Promote your work: by contacting scholars who work in the same
field, giving talks, conference presentations, etc.
• Collaborate with scholars who have an established research
record (and citations)
• Rewrite old pieces of research (which have not earned many
citations) – different audience, perhaps with an application
• Also write review papers and books
• Fight the fragmentation of our field (build bridges) – we are no
longer a small field, but fragmented

13

You might also like