Skip to main content

Mapping Knowledge Domains (2004) / Chapter Skim
Currently Skimming:

Evolution of document networks
Pages 79-83

The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.


From page 79...
... Some theories have explored similar mixture models in which links are created according to a trade-off between graph degree and metric distance measures, showing that certain trade-off regimes lead to power-law degree distributions (26, 27~. To study the decision process by which authors link documents, let us consider the relationship between the probability that two documents are linked and their content (text)
Read the entire page →
From page 80...
... This degree-similarity phase model accurately predicted the degree distribution of the web pages in the 5262 1 www.pnas.org/cgi/doi/10. 1 073/pnas.0307554100 Fl l all pairs DMOZ + linked pairs DMOZ x all pairs PNAS 3< linked pairs PNAS .
Read the entire page →
From page 81...
... Although both models accurately predict the degree distribution, only the degree-similarity mixture model reasonably approximates the similarity distribution. The PNAS article data were analyzed analogously to the DMOZ data, yielding a conditional citation probability with a tail that scales as a power-law Pr(A = 0.1~K)
Read the entire page →
From page 82...
... This model generates remarkably accurate predictions of how such a process can lead to the emergent link and content structure of document spaces. I thank Jon Kleinberg, Rob Axtell, David Aldous, Laszlo Barabasi, Reka Albert, Mark Newman, Lada Adamic, Alessandro Vespignani, and Katy Borner for reviewing an earlier draft of this manuscript; Rich Shiffrin and two anonymous reviewers for providing helpful suggestions; the Open Directory Project for the DMOZ data; and the National Academy of Sciences for the PNAS data.
Read the entire page →
From page 83...
... (2002) in Proceedings of the 29th International Colloquium onAutomata, Languages, and Programming, Lecture Menczer Notes in Computer Science, eds.
Read the entire page →

Key Terms

  • mixture model
  • degree distributions
  • degree distribution
  • information networks
  • link similarity

  • model generates
  • link probability
  • preferential attachment
  • mixture models
  • content similarity

  • attachment model
  • directory project
  • pnas articles
  • remarkably accurate
  • scientific articles

  • dmoz data
  • textual similarity
  • accurate predictions
  • phase model
  • linked documents

  • generates networks
  • link analysis
  • knowledge owing
  • knowledge domains
  • similarity distribution

  • metric defined
  • jaccard coefficient
  • popular documents
  • maps demonstrate
  • pages predicted


    • This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
    More information on Chapter Skim is available.