Castillo, C (Castillo, Carlos); Donato, D (Donato, Debora); Gionis, A (Gionis, Aristides) Estimating number of citations using author reputation STRING PROCESSING AND INFORMATION RETRIEVAL, PROCEEDINGS 107-117, 2007

[Eugene Garfield]

Email address: chato at chato.cl (in first email to author, please 
include 'baldor' in the subject line)

Author(s): Castillo, C (Castillo, Carlos); Donato, D (Donato, Debora); 
Gionis, A (Gionis, Aristides) 

Title: Estimating number of citations using author reputation 

Editor(s): Ziviani, N; BaezaYates, R 

Source: STRING PROCESSING AND INFORMATION RETRIEVAL, PROCEEDINGS 107-117, 
2007 

Book Series: LECTURE NOTES IN COMPUTER SCIENCE, 4726 

Language: English 

Document Type: Article 

Conference Title: 14th International Symposium on String Processing and 
Information Retrieval 

Conference Date: OCT 29-31, 2007 

Conference Location: Santiago, CHILE 

Conference Sponsors: Univ Chile, Dept Comp Sci, Web Res, Millwnnium Nucl 
Ctr, Fed Univ Minas Gerais, Dept Comp Sci, Yahoo, Res Latin Amer 

Abstract: We study the problem of predicting the popularity of items in a 
dynamic environment in which authors post continuously new items and 
provide feedback on existing items. This problem can be applied to predict 
popularity of blog posts, rank photographs in a photo-sharing system, or 
predict the citations of a scientific article using author information and 
monitoring the items of interest for a short period of time after their 
creation. As a case study, we show how to estimate the number of citations 
for an academic paper using information about past articles written by the 
same author(s) of the paper. If we use only the citation information over 
a short period of time, we obtain a predicted value that has a correlation 
of r = 0.57 with the actual value. This is our baseline prediction. Our 
best-performing system can improve that prediction by adding features 
extracted from the past publishing history of its authors, increasing the 
correlation between the actual and the predicted values to r = 0.81. 

Addresses: Yahoo Res Barcelona, Barcelona, Catalunya 08003 Spain. 

Reprint Address: Castillo, C, Yahoo Res Barcelona, C Ocata 1, Barcelona, 
Catalunya 08003 Spain. 

Publisher Name: SPRINGER-VERLAG BERLIN 

Publisher Address: HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY 

ISSN: 0302-9743 

Cited Reference Count: 16 

ADAR E
WWE 2004 NEW YORK US : 2004 

BAEZAYATES R
LNCS 2476 : 2002 

BURIOL L
WI 2006 HONG KONG : 45 2006 

CHO J
SIGMOD 2005 : 551 2005 

FEITELSON DG
Predictive ranking of computer scientists using CiteSeer data
J DOC 60 : 44 2004 

FUJIMURA K
The EigenRumor algorithm for calculating contributions in cyberspace 
communities 
TRUSTING AGENTS FOR TRUSTING ELECTRONIC SOCIETIES: THEORY AND APPLICATIONS 
IN HCI AND E-COMMERCE 3577 : 59 2005 

GEHRKE J
SIGKDD EXPLOR NEWSL 5 : 149 2003 

KLEINBERG JM
Authoritative sources in a hyperlinked environment
J ACM 46 : 604 1999 

KUMAR R
Structure and evolution of blogspaceCOMMUN ACM 47 : 35 2004 

LESKOVEC J
KDD 05 : 177 2005 

LIBENNOWELL D
CIKM 03 P 12 INT C I : 556 2003 

MEI Q
WWW 2006 : 533 2006 

PAGE L
PAGERANK CITATION RA : 1998 

POPESCUL A
IJCAI 2003 : 2003 

SALGANIK MJ
Experimental study of inequality and unpredictability in an artificial 
cultural market
SCIENCE 311 : 854 2006 

WITTEN IH
DATA MINING PRACTICA : 1999