Detecting innovative topics based on user-interest ontology

Makoto Nakatsuji, Makoto Yoshida, Toru Ishida

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

In this paper, we detect "innovative topics", those that are new and hopefully interesting to the user. We try to expand user interests significantly by letting the user browse those topics. We first generate user-interest ontologies that allow user profiles to be constructed as a hierarchy of classes where a user interest weight is assigned to each class and instance. Next, we measure the similarity between user interests by using interest weights on their user-interest ontologies and generate user group GU that has high similarity to user u. The innovative topics for u are then detected by determining a suitable size of GU and analyzing the ontologies in GU.

Original languageEnglish
Pages (from-to)107-120
Number of pages14
JournalWeb Semantics
Volume7
Issue number2
DOIs
Publication statusPublished - 2009 Apr 1
Externally publishedYes

Fingerprint

Ontology

Keywords

  • Detecting innovative topics
  • Measuring similarity between ontologies
  • User-interest ontology

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Networks and Communications

Cite this

Detecting innovative topics based on user-interest ontology. / Nakatsuji, Makoto; Yoshida, Makoto; Ishida, Toru.

In: Web Semantics, Vol. 7, No. 2, 01.04.2009, p. 107-120.

Research output: Contribution to journalArticle

Nakatsuji, Makoto ; Yoshida, Makoto ; Ishida, Toru. / Detecting innovative topics based on user-interest ontology. In: Web Semantics. 2009 ; Vol. 7, No. 2. pp. 107-120.
@article{eb8ee088b8fc488a9cfb17a58980ae0c,
title = "Detecting innovative topics based on user-interest ontology",
abstract = "In this paper, we detect {"}innovative topics{"}, those that are new and hopefully interesting to the user. We try to expand user interests significantly by letting the user browse those topics. We first generate user-interest ontologies that allow user profiles to be constructed as a hierarchy of classes where a user interest weight is assigned to each class and instance. Next, we measure the similarity between user interests by using interest weights on their user-interest ontologies and generate user group GU that has high similarity to user u. The innovative topics for u are then detected by determining a suitable size of GU and analyzing the ontologies in GU.",
keywords = "Detecting innovative topics, Measuring similarity between ontologies, User-interest ontology",
author = "Makoto Nakatsuji and Makoto Yoshida and Toru Ishida",
year = "2009",
month = "4",
day = "1",
doi = "10.1016/j.websem.2009.01.001",
language = "English",
volume = "7",
pages = "107--120",
journal = "Web Semantics",
issn = "1570-8268",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Detecting innovative topics based on user-interest ontology

AU - Nakatsuji, Makoto

AU - Yoshida, Makoto

AU - Ishida, Toru

PY - 2009/4/1

Y1 - 2009/4/1

N2 - In this paper, we detect "innovative topics", those that are new and hopefully interesting to the user. We try to expand user interests significantly by letting the user browse those topics. We first generate user-interest ontologies that allow user profiles to be constructed as a hierarchy of classes where a user interest weight is assigned to each class and instance. Next, we measure the similarity between user interests by using interest weights on their user-interest ontologies and generate user group GU that has high similarity to user u. The innovative topics for u are then detected by determining a suitable size of GU and analyzing the ontologies in GU.

AB - In this paper, we detect "innovative topics", those that are new and hopefully interesting to the user. We try to expand user interests significantly by letting the user browse those topics. We first generate user-interest ontologies that allow user profiles to be constructed as a hierarchy of classes where a user interest weight is assigned to each class and instance. Next, we measure the similarity between user interests by using interest weights on their user-interest ontologies and generate user group GU that has high similarity to user u. The innovative topics for u are then detected by determining a suitable size of GU and analyzing the ontologies in GU.

KW - Detecting innovative topics

KW - Measuring similarity between ontologies

KW - User-interest ontology

UR - http://www.scopus.com/inward/record.url?scp=65149092478&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=65149092478&partnerID=8YFLogxK

U2 - 10.1016/j.websem.2009.01.001

DO - 10.1016/j.websem.2009.01.001

M3 - Article

AN - SCOPUS:65149092478

VL - 7

SP - 107

EP - 120

JO - Web Semantics

JF - Web Semantics

SN - 1570-8268

IS - 2

ER -