Discrimination of personal web pages by extracting subjective expressions

Takahiro Hayashi, Koji Abe, Debabrata Roy, Rikio Onai

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper presents a method for discriminating between personal and non-personal web pages. The method can support surveys of personal opinions about products and services. In the proposed method, subjective expressions are extracted from pages and then the pages are scored by quantitatively evaluating the subjectivity in the pages. We have evaluated performances of the proposed method using 1200 web pages collected from four categories of product, tourist spot, restaurant, and movie. Comparing the performances of the proposed method with categorisations by a general search engine, we have confirmed that the performances have been significantly better in every category.

Original languageEnglish
Pages (from-to)62-77
Number of pages16
JournalInternational Journal of Business Intelligence and Data Mining
Volume4
Issue number1
DOIs
Publication statusPublished - 2009
Externally publishedYes

Fingerprint

Discrimination
Websites
Search engines
Categorization
Search Engine
World Wide Web

Keywords

  • Dcument classification
  • Personal web pages
  • Subjective expressions

ASJC Scopus subject areas

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

Cite this

Discrimination of personal web pages by extracting subjective expressions. / Hayashi, Takahiro; Abe, Koji; Roy, Debabrata; Onai, Rikio.

In: International Journal of Business Intelligence and Data Mining, Vol. 4, No. 1, 2009, p. 62-77.

Research output: Contribution to journalArticle

Hayashi, Takahiro ; Abe, Koji ; Roy, Debabrata ; Onai, Rikio. / Discrimination of personal web pages by extracting subjective expressions. In: International Journal of Business Intelligence and Data Mining. 2009 ; Vol. 4, No. 1. pp. 62-77.
@article{7ff3acf226f34126b347d5477b2b9db1,
title = "Discrimination of personal web pages by extracting subjective expressions",
abstract = "This paper presents a method for discriminating between personal and non-personal web pages. The method can support surveys of personal opinions about products and services. In the proposed method, subjective expressions are extracted from pages and then the pages are scored by quantitatively evaluating the subjectivity in the pages. We have evaluated performances of the proposed method using 1200 web pages collected from four categories of product, tourist spot, restaurant, and movie. Comparing the performances of the proposed method with categorisations by a general search engine, we have confirmed that the performances have been significantly better in every category.",
keywords = "Dcument classification, Personal web pages, Subjective expressions",
author = "Takahiro Hayashi and Koji Abe and Debabrata Roy and Rikio Onai",
year = "2009",
doi = "10.1504/IJBIDM.2009.025411",
language = "English",
volume = "4",
pages = "62--77",
journal = "International Journal of Business Intelligence and Data Mining",
issn = "1743-8187",
publisher = "Inderscience Enterprises Ltd",
number = "1",

}

TY - JOUR

T1 - Discrimination of personal web pages by extracting subjective expressions

AU - Hayashi, Takahiro

AU - Abe, Koji

AU - Roy, Debabrata

AU - Onai, Rikio

PY - 2009

Y1 - 2009

N2 - This paper presents a method for discriminating between personal and non-personal web pages. The method can support surveys of personal opinions about products and services. In the proposed method, subjective expressions are extracted from pages and then the pages are scored by quantitatively evaluating the subjectivity in the pages. We have evaluated performances of the proposed method using 1200 web pages collected from four categories of product, tourist spot, restaurant, and movie. Comparing the performances of the proposed method with categorisations by a general search engine, we have confirmed that the performances have been significantly better in every category.

AB - This paper presents a method for discriminating between personal and non-personal web pages. The method can support surveys of personal opinions about products and services. In the proposed method, subjective expressions are extracted from pages and then the pages are scored by quantitatively evaluating the subjectivity in the pages. We have evaluated performances of the proposed method using 1200 web pages collected from four categories of product, tourist spot, restaurant, and movie. Comparing the performances of the proposed method with categorisations by a general search engine, we have confirmed that the performances have been significantly better in every category.

KW - Dcument classification

KW - Personal web pages

KW - Subjective expressions

UR - http://www.scopus.com/inward/record.url?scp=66349095657&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=66349095657&partnerID=8YFLogxK

U2 - 10.1504/IJBIDM.2009.025411

DO - 10.1504/IJBIDM.2009.025411

M3 - Article

AN - SCOPUS:66349095657

VL - 4

SP - 62

EP - 77

JO - International Journal of Business Intelligence and Data Mining

JF - International Journal of Business Intelligence and Data Mining

SN - 1743-8187

IS - 1

ER -