Exploiting Relational Structure to Understand Publication Patterns in HighEnergy Physics

1
Exploiting Relational Structure to Understand
Publication Patterns in High-Energy Physics

• Amy McGovern, Lisa Friedland, Michael Hay, Brian
  Gallagher, Andrew Fast, Jennifer Neville, David
  Jensen
• Knowledge Discovery LaboratoryUniversity of
  Massachusetts Amherst

2
Knowledge Discovery Process
Data cleaning
Data extraction
Data analysis
Citation analysis
Identifying research communities
Predicting journal publication
Understanding author influence
Data dependencies
Implemented using KDLs PROXIMITY software
3
Data cleaning and extraction

• Extracted abstracts
• Consolidated authors
• Same name assumed
• 13,185 authors to 9,200
• Co-authored with similar names
• Authors of referenced papers with similar names
• Authors with similar email domains and the same
  username

Relational schema
4
Data dependencies

• Examples of high correlations
• Number of downloads in first 60 days and number
  of citations
• Is paper published and number of citations
  (binned)
• Examples of high autocorrelation
• Journal name (through author)
• Topic cluster of paper (through author)
• Authors total co-authors (through paper)
• Number of downloads in first 60 days (through
  journal)

High autocorrelation
Low autocorrelation
5
Influential Authors
6
20 of physicists receive 80 of the citations
7
Influential authors are more connected
8
Will a paper be accepted by Physics Letters B?

• Papers from 1995-2000
• 68 accuracy, 0.75 AUC

9
Identifying Research Communities

• Spectral clustering on citation graph and
  abstracts
• Papers from 1995 to 2000

10
Example topic clusters
Cluster 2 Black hole approach to string theory
Sumit R.Das (251), Physical Review D Absorption
of Fixed scalars and the D-brane Approach to
Black Holes Universal Low-Energy Dynamics for
Rotating Black Holes Interactions involving
D-branes Black Hole Greybody Factors and D-Brane
Spectroscopy Cluster 10 Tachyon
Condensation Juan M. Maldacena (1924), Journal
of High Energy Physics Field theory models for
tachyon and gauge field string dynamics Super-Poin
care Invariant Superstring Field Theory Level
Four Approximation to the Tachyon Potential in
Superstring Field Theory SO(32) Spinors of Type I
and Other Solitons on Brane-Antibrane Pair
11
KDD Cup 2003 Paperkdl.cs.umass.edu/papers/kddcup
2003.htmlProximitykdl.cs.umass.edu/proximity/
Emailamy_at_cs.umass.edu