Vote prediction by iterative domain knowledge and attribute elimination

Anthony Scime, Gregory Roy Murray

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Data mining the American National Election Study (ANES), a rich but disparate source of information about Americans' vote choices, is the focus of this research. Specifically, we use data mining classification to construct a decision tree to select important predictors of the vote from the more than 900 items that compose the ANES. We use an iterative domain expert and data mining process to identify a limited number of survey questions intended to predict for which party an individual will vote in a presidential election or whether that individual will vote at all.

Original languageEnglish (US)
Pages (from-to)160-176
Number of pages17
JournalInternational Journal of Business Intelligence and Data Mining
Volume2
Issue number2
DOIs
StatePublished - Jul 2 2007
Externally publishedYes

Fingerprint

Domain Knowledge
Vote
Data mining
Elimination
Elections
Attribute
Data Mining
Prediction
Decision trees
Decision tree
Predictors
Predict
Domain knowledge

Keywords

  • Classification
  • Data mining
  • Dimensionality reduction
  • Domain expert
  • Domain knowledge
  • Elections
  • Information gain
  • Political science
  • Prediction
  • Voting

ASJC Scopus subject areas

  • Management Information Systems
  • Statistics, Probability and Uncertainty
  • Information Systems and Management

Cite this

Vote prediction by iterative domain knowledge and attribute elimination. / Scime, Anthony; Murray, Gregory Roy.

In: International Journal of Business Intelligence and Data Mining, Vol. 2, No. 2, 02.07.2007, p. 160-176.

Research output: Contribution to journalArticle

@article{8863cdc6d4a74fb09fa135a35bb94e12,
title = "Vote prediction by iterative domain knowledge and attribute elimination",
abstract = "Data mining the American National Election Study (ANES), a rich but disparate source of information about Americans' vote choices, is the focus of this research. Specifically, we use data mining classification to construct a decision tree to select important predictors of the vote from the more than 900 items that compose the ANES. We use an iterative domain expert and data mining process to identify a limited number of survey questions intended to predict for which party an individual will vote in a presidential election or whether that individual will vote at all.",
keywords = "Classification, Data mining, Dimensionality reduction, Domain expert, Domain knowledge, Elections, Information gain, Political science, Prediction, Voting",
author = "Anthony Scime and Murray, {Gregory Roy}",
year = "2007",
month = "7",
day = "2",
doi = "10.1504/IJBIDM.2007.013935",
language = "English (US)",
volume = "2",
pages = "160--176",
journal = "International Journal of Business Intelligence and Data Mining",
issn = "1743-8187",
publisher = "Inderscience Enterprises Ltd",
number = "2",

}

TY - JOUR

T1 - Vote prediction by iterative domain knowledge and attribute elimination

AU - Scime, Anthony

AU - Murray, Gregory Roy

PY - 2007/7/2

Y1 - 2007/7/2

N2 - Data mining the American National Election Study (ANES), a rich but disparate source of information about Americans' vote choices, is the focus of this research. Specifically, we use data mining classification to construct a decision tree to select important predictors of the vote from the more than 900 items that compose the ANES. We use an iterative domain expert and data mining process to identify a limited number of survey questions intended to predict for which party an individual will vote in a presidential election or whether that individual will vote at all.

AB - Data mining the American National Election Study (ANES), a rich but disparate source of information about Americans' vote choices, is the focus of this research. Specifically, we use data mining classification to construct a decision tree to select important predictors of the vote from the more than 900 items that compose the ANES. We use an iterative domain expert and data mining process to identify a limited number of survey questions intended to predict for which party an individual will vote in a presidential election or whether that individual will vote at all.

KW - Classification

KW - Data mining

KW - Dimensionality reduction

KW - Domain expert

KW - Domain knowledge

KW - Elections

KW - Information gain

KW - Political science

KW - Prediction

KW - Voting

UR - http://www.scopus.com/inward/record.url?scp=34250885168&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250885168&partnerID=8YFLogxK

U2 - 10.1504/IJBIDM.2007.013935

DO - 10.1504/IJBIDM.2007.013935

M3 - Article

AN - SCOPUS:34250885168

VL - 2

SP - 160

EP - 176

JO - International Journal of Business Intelligence and Data Mining

JF - International Journal of Business Intelligence and Data Mining

SN - 1743-8187

IS - 2

ER -