An article kansei retrieval system combining recommendation function and interaction design

Yuichi Murakami, Shingo Nakamura, Shuji Hashimoto

Research output: Contribution to journalArticle

Abstract

In most article retrieval systems using Kansei words there exists a gap between user's Kansei and the system's Kansei model. Therefore, it is not always easy to retrieve the desirable articles. The purpose of this paper is to bridge this gap not to put a strain on users by combining the recommendation function and interaction design with four features. First, users can retrieve intuitively as the system visualizes retrieval space consisting of a torus type SOM (Self Organizing Maps). Second, users can find the most desirable article in any case by elimination methods to delete undesirable articles pointed by the user. Third, neural networks in the system learn user's Kansei based on the most desirable article to improve the retrieval accuracy. Fourth, users can search articles by arbitrary Kansei words, and can edit retrieval criteria as they please. In the evaluation experiments, the authors took actual paintings as the articles, and evaluated usability (effectiveness, efficiency and satisfaction), novelty and serendipity. These results were led by the synergetic effects of the recommendation function and interaction design.

Original languageEnglish
Pages (from-to)548-558
Number of pages11
JournalJournal of Information Processing
Volume20
Issue number3
DOIs
Publication statusPublished - 2012
Externally publishedYes

Fingerprint

Recommender systems
Self organizing maps
Painting
Neural networks
Experiments

Keywords

  • Human computer interaction
  • Intelligent user interface
  • Kansei information processing
  • Personalization
  • Web retrieval

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

An article kansei retrieval system combining recommendation function and interaction design. / Murakami, Yuichi; Nakamura, Shingo; Hashimoto, Shuji.

In: Journal of Information Processing, Vol. 20, No. 3, 2012, p. 548-558.

Research output: Contribution to journalArticle

@article{908ec9f70c2f4e53894b124e744e08b1,
title = "An article kansei retrieval system combining recommendation function and interaction design",
abstract = "In most article retrieval systems using Kansei words there exists a gap between user's Kansei and the system's Kansei model. Therefore, it is not always easy to retrieve the desirable articles. The purpose of this paper is to bridge this gap not to put a strain on users by combining the recommendation function and interaction design with four features. First, users can retrieve intuitively as the system visualizes retrieval space consisting of a torus type SOM (Self Organizing Maps). Second, users can find the most desirable article in any case by elimination methods to delete undesirable articles pointed by the user. Third, neural networks in the system learn user's Kansei based on the most desirable article to improve the retrieval accuracy. Fourth, users can search articles by arbitrary Kansei words, and can edit retrieval criteria as they please. In the evaluation experiments, the authors took actual paintings as the articles, and evaluated usability (effectiveness, efficiency and satisfaction), novelty and serendipity. These results were led by the synergetic effects of the recommendation function and interaction design.",
keywords = "Human computer interaction, Intelligent user interface, Kansei information processing, Personalization, Web retrieval",
author = "Yuichi Murakami and Shingo Nakamura and Shuji Hashimoto",
year = "2012",
doi = "10.2197/ipsjjip.20.548",
language = "English",
volume = "20",
pages = "548--558",
journal = "Journal of Information Processing",
issn = "0387-5806",
publisher = "Information Processing Society of Japan",
number = "3",

}

TY - JOUR

T1 - An article kansei retrieval system combining recommendation function and interaction design

AU - Murakami, Yuichi

AU - Nakamura, Shingo

AU - Hashimoto, Shuji

PY - 2012

Y1 - 2012

N2 - In most article retrieval systems using Kansei words there exists a gap between user's Kansei and the system's Kansei model. Therefore, it is not always easy to retrieve the desirable articles. The purpose of this paper is to bridge this gap not to put a strain on users by combining the recommendation function and interaction design with four features. First, users can retrieve intuitively as the system visualizes retrieval space consisting of a torus type SOM (Self Organizing Maps). Second, users can find the most desirable article in any case by elimination methods to delete undesirable articles pointed by the user. Third, neural networks in the system learn user's Kansei based on the most desirable article to improve the retrieval accuracy. Fourth, users can search articles by arbitrary Kansei words, and can edit retrieval criteria as they please. In the evaluation experiments, the authors took actual paintings as the articles, and evaluated usability (effectiveness, efficiency and satisfaction), novelty and serendipity. These results were led by the synergetic effects of the recommendation function and interaction design.

AB - In most article retrieval systems using Kansei words there exists a gap between user's Kansei and the system's Kansei model. Therefore, it is not always easy to retrieve the desirable articles. The purpose of this paper is to bridge this gap not to put a strain on users by combining the recommendation function and interaction design with four features. First, users can retrieve intuitively as the system visualizes retrieval space consisting of a torus type SOM (Self Organizing Maps). Second, users can find the most desirable article in any case by elimination methods to delete undesirable articles pointed by the user. Third, neural networks in the system learn user's Kansei based on the most desirable article to improve the retrieval accuracy. Fourth, users can search articles by arbitrary Kansei words, and can edit retrieval criteria as they please. In the evaluation experiments, the authors took actual paintings as the articles, and evaluated usability (effectiveness, efficiency and satisfaction), novelty and serendipity. These results were led by the synergetic effects of the recommendation function and interaction design.

KW - Human computer interaction

KW - Intelligent user interface

KW - Kansei information processing

KW - Personalization

KW - Web retrieval

UR - http://www.scopus.com/inward/record.url?scp=84871224499&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871224499&partnerID=8YFLogxK

U2 - 10.2197/ipsjjip.20.548

DO - 10.2197/ipsjjip.20.548

M3 - Article

AN - SCOPUS:84871224499

VL - 20

SP - 548

EP - 558

JO - Journal of Information Processing

JF - Journal of Information Processing

SN - 0387-5806

IS - 3

ER -