An Algorithm to Tackle the Name Authority Control Problem Using Semantic Information

Name disambiguation is a focal point on realworld information integration, analysis, and data mining. This problem, also known as the classical name authority control problem, consists in "same authors with different spellings" or "different authors with the same spelling". The p...

Full description

Saved in:
Bibliographic Details
Main Authors: Chavez-Aragon, Alberto, Cruz, Jose Federico Ramirez, Reyes-Galaviz, Orion F, Ayanegui-Santiago, Huberto, Portilla, Alberto
Format: Conference Proceeding
Language:English
Subjects:
Bibliographies
Computer science
Data analysis
Data mining
identity uncertainty
Informatics
Information analysis
Information retrieval
Laboratories
name authority control problem
Name disambiguation
Publishing
semantic information
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Name disambiguation is a focal point on realworld information integration, analysis, and data mining. This problem, also known as the classical name authority control problem, consists in "same authors with different spellings" or "different authors with the same spelling". The problem is augmented in large data repositories where information changes and grows over time (e.g., DBLP, CiteSeer). In particular, we are mainly interested in DBLP because we use this database to discover the publishing movement among Mexican researchers. In this paper, we propose an algorithm that solves the name authority control problem. Our approach aims to improve the identity author tracking by using semantic information about authors, even thought they use different name varieties to sign their research work over time.
DOI:10.1109/ENC.2009.38