Knowledge structure for information professionals

1
Knowledge structure for information professionals

• Lecture 2 Intro to bibliometrics

2
Bibliometrics

• biblio derived from biblion Greek word for
  book
• metrics derived from metrikos Greek word for
  measurement

3
Traditional definition

• The quantitative study of literature as they are
  reflected in bibliographies (White and McCain
  1989).
• The study of patterns of authorship, publication
  and literature use by applying various
  statistical analyses (Lancaster, 1977).

4
Alternative definition the behavioral element

• the study of the application of statistical
  methods to the study of ...human
  document-related behavior,
• specifically, behavior that involves (i)
  determining, (ii) expressing, or (iii) acting
  on, preferences for documents (Jonathan Furner)

5
Reader/User-centered bibliometrics

• new kinds of document
• electronic documents, non-scholarly documents
• new kinds of behavior
• Hypertext linking, mentioning, retrieval, usage,
• purchasing (e.g., frequency of link activation,
  hit-
• rate, frequency of download, time spent viewing)

6
Object and assumption (Furner)

• objective the analysis of human preferences for
  documents, in order to
• reward authors,
• recommend documents, or
• represent document-network structure
• assumption any action of writing, publishing,
  citing, reading, viewing, or buying a document at
  any given time is the outcome of a decision to
  select that document rather than any other
• i.e., the action is an expression of a preference
  ordering over the universal set of documents

7
Major areas of bibliometric research

• Indicators of research performance
• Citation analysis
• Bibliometric laws (Bradfords law, Lotkas law,
  Zipfs law)

8
Application for bibliometrics

• in resource distribution
• identifying authors most worthy of promotion
  research
• areas most worthy of funding journals most
  worthy of
• purchase etc.
• in collection development
• identifying the most-useful materials by
  analyzing circulation
• records journal / e-journal usage statistics
  etc.
• in information retrieval
• identifying top-ranked documents, authors those
  most highly-cited
• most highly co-cited most popular etc.
• in the sociology of knowledge
• identifying structural and temporal relationships
  between
• documents, authors, research areas, etc.

9
ISI Citation index

• The Web of Science is an enhanced web version of
  the Institute for Scientific Information's
  citation indexes, including the Science Citation
  Index, the Social Sciences Citation Index, and
  the Arts and Humanities Citation Index.
• The Web of Science measures the impact of
  particular journals and is one of the sources
  used by the National Research Council to rank
  graduate programs

10
ISI indicators

• Impact factors
• B total citations in 2001 to articles in
  journal X published
• 1999-2000
• C number of journal X articles published
  1999-2000
• 2001 impact factor of journal X B/C
• Immediacy index

11
Cited half-life

• Definition the number of years that the number
  of citations take to decline to 50 of its
  current total value.
• a measure of how long articles in a journal
  continue to be cited after publication.

12
Citing half-life

• Definition the median age of all cited articles
  in the journal during the year.
• A measure of how current the references cited in
  the journal

13
Source (Amin Mabe 2000)
14
Citation analysis

• Bibliographic coupling
• Document co-citation analysis
• Author co-citation analysis

15
Subject variation
Source (Amin Mabe 2000)
16
Bibliographic coupling

• The assumption two documents both cite the same
  previously published docs have something in
  common.
• The strength of bibliographic coupling depends on
  the number of references the two papers have in
  common.
• results in a cluster of citing documents
• is fixed and permanent

17
Co-citation coupling

• Number of times two documents are jointly cited
  in later publication,
• results in a cluster of cited docs (a research
  front)
• Co-citation patterns change as the interests
  and intellectual patterns of the field changes

18
Co-citation strength

• S co-citations of A B /citations either A or B
  
• (Small 1973)

19
Fractional citation counting

• Reference length bias
• Each citing item has a total voting strength of
  one, but divides that single vote equally among
  all references it cites. If an item contains ten
  references, each citation has a fractional weight
  of 1/10

20
Link-based indexing
PageRank relies on the democratic nature of the
web by using its vast link structure as an
indicator of an individual pages value, An
in-link to a page is considered as a vote to the
authority of the page.
21
PageRank

• Votes cast by pages that are themselves
  "important"
• weigh more heavily and help to make other pages
• "important."
• PR (A) (1-d) d (PR (t1)/C(t1) (PR
  (t2)/C(t2) .. (PR (tn)/C(tn)
• PR pack rank
• t1 tn are pages linking to page A,
• C is the number of outbound links that a page has
• d is a damping factor, usually set to .85
• In plain language
• A pages PageRank 0.15 0.85 (a share of
  the PageRank of every page
• that link to it)

22
The reasons to cite

• Garfield
• Budd
• Small

23
Cited document as concept symbols

• By condensing or capsulizing a complex
  original text into a few standard statements, the
  community of scientists can more easily confirm,
  refute or build upon the earlier work. This
  serves the needs of the specialty by enabling
  work to go on unencumbered by the necessity of
  unraveling the complete meaning and implications
  of the earlier text, even though this may result
  in the distortion or oversimplification of the
  original
• (Small 1978, p. 338)