An article retrieval support system that learns user's Kansei

Yuichi Murakami, Shingo Nakamura, Shuji Hashimoto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Most of article retrieval systems using retrieval criteria of Kansei words have a gap between user's Kansei and system's Kansei model. Therefore, it is not always easy to retrieve the desired articles efficiently according to the user's preference. This paper proposed a system to retrieve the desired articles quickly and intuitively from the database. To achieve this aim, dimension of the retrieval space is compressed by a torus SOM (Self Organizing Maps), and a user can move in the retrieval space panoramically. A user can also choose an elimination method during search. By this method, the system estimates the significant Kansei parameters and makes the search more efficient. The system also has a function to eliminate the unselected articles and reduces the size of SOM. Additionally, the system learns the Kansei of individual user from the retrieval results by using neural networks. In evaluation experiments, we took actual painting as article, and confirmed the efficacy of the proposed method.

Original languageEnglish
Title of host publicationProceedings - 2010 International Conference on User Science and Engineering, i-USEr 2010
Pages32-37
Number of pages6
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event1st International Conference on User Science and Engineering 2010, iUSEr 2010 - Shah Alam, Malaysia
Duration: 2010 Dec 132010 Dec 15

Other

Other1st International Conference on User Science and Engineering 2010, iUSEr 2010
CountryMalaysia
CityShah Alam
Period10/12/1310/12/15

Fingerprint

Self organizing maps
Painting
Neural networks
Experiments

Keywords

  • Kansei
  • Neural networks
  • Retrieval support system
  • Torus SOM

ASJC Scopus subject areas

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

Cite this

Murakami, Y., Nakamura, S., & Hashimoto, S. (2010). An article retrieval support system that learns user's Kansei. In Proceedings - 2010 International Conference on User Science and Engineering, i-USEr 2010 (pp. 32-37). [5716718] https://doi.org/10.1109/IUSER.2010.5716718

An article retrieval support system that learns user's Kansei. / Murakami, Yuichi; Nakamura, Shingo; Hashimoto, Shuji.

Proceedings - 2010 International Conference on User Science and Engineering, i-USEr 2010. 2010. p. 32-37 5716718.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Murakami, Y, Nakamura, S & Hashimoto, S 2010, An article retrieval support system that learns user's Kansei. in Proceedings - 2010 International Conference on User Science and Engineering, i-USEr 2010., 5716718, pp. 32-37, 1st International Conference on User Science and Engineering 2010, iUSEr 2010, Shah Alam, Malaysia, 10/12/13. https://doi.org/10.1109/IUSER.2010.5716718
Murakami Y, Nakamura S, Hashimoto S. An article retrieval support system that learns user's Kansei. In Proceedings - 2010 International Conference on User Science and Engineering, i-USEr 2010. 2010. p. 32-37. 5716718 https://doi.org/10.1109/IUSER.2010.5716718
Murakami, Yuichi ; Nakamura, Shingo ; Hashimoto, Shuji. / An article retrieval support system that learns user's Kansei. Proceedings - 2010 International Conference on User Science and Engineering, i-USEr 2010. 2010. pp. 32-37
@inproceedings{ed6f22292de548b1b999f31423583e01,
title = "An article retrieval support system that learns user's Kansei",
abstract = "Most of article retrieval systems using retrieval criteria of Kansei words have a gap between user's Kansei and system's Kansei model. Therefore, it is not always easy to retrieve the desired articles efficiently according to the user's preference. This paper proposed a system to retrieve the desired articles quickly and intuitively from the database. To achieve this aim, dimension of the retrieval space is compressed by a torus SOM (Self Organizing Maps), and a user can move in the retrieval space panoramically. A user can also choose an elimination method during search. By this method, the system estimates the significant Kansei parameters and makes the search more efficient. The system also has a function to eliminate the unselected articles and reduces the size of SOM. Additionally, the system learns the Kansei of individual user from the retrieval results by using neural networks. In evaluation experiments, we took actual painting as article, and confirmed the efficacy of the proposed method.",
keywords = "Kansei, Neural networks, Retrieval support system, Torus SOM",
author = "Yuichi Murakami and Shingo Nakamura and Shuji Hashimoto",
year = "2010",
doi = "10.1109/IUSER.2010.5716718",
language = "English",
isbn = "9781424490493",
pages = "32--37",
booktitle = "Proceedings - 2010 International Conference on User Science and Engineering, i-USEr 2010",

}

TY - GEN

T1 - An article retrieval support system that learns user's Kansei

AU - Murakami, Yuichi

AU - Nakamura, Shingo

AU - Hashimoto, Shuji

PY - 2010

Y1 - 2010

N2 - Most of article retrieval systems using retrieval criteria of Kansei words have a gap between user's Kansei and system's Kansei model. Therefore, it is not always easy to retrieve the desired articles efficiently according to the user's preference. This paper proposed a system to retrieve the desired articles quickly and intuitively from the database. To achieve this aim, dimension of the retrieval space is compressed by a torus SOM (Self Organizing Maps), and a user can move in the retrieval space panoramically. A user can also choose an elimination method during search. By this method, the system estimates the significant Kansei parameters and makes the search more efficient. The system also has a function to eliminate the unselected articles and reduces the size of SOM. Additionally, the system learns the Kansei of individual user from the retrieval results by using neural networks. In evaluation experiments, we took actual painting as article, and confirmed the efficacy of the proposed method.

AB - Most of article retrieval systems using retrieval criteria of Kansei words have a gap between user's Kansei and system's Kansei model. Therefore, it is not always easy to retrieve the desired articles efficiently according to the user's preference. This paper proposed a system to retrieve the desired articles quickly and intuitively from the database. To achieve this aim, dimension of the retrieval space is compressed by a torus SOM (Self Organizing Maps), and a user can move in the retrieval space panoramically. A user can also choose an elimination method during search. By this method, the system estimates the significant Kansei parameters and makes the search more efficient. The system also has a function to eliminate the unselected articles and reduces the size of SOM. Additionally, the system learns the Kansei of individual user from the retrieval results by using neural networks. In evaluation experiments, we took actual painting as article, and confirmed the efficacy of the proposed method.

KW - Kansei

KW - Neural networks

KW - Retrieval support system

KW - Torus SOM

UR - http://www.scopus.com/inward/record.url?scp=79952858769&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952858769&partnerID=8YFLogxK

U2 - 10.1109/IUSER.2010.5716718

DO - 10.1109/IUSER.2010.5716718

M3 - Conference contribution

SN - 9781424490493

SP - 32

EP - 37

BT - Proceedings - 2010 International Conference on User Science and Engineering, i-USEr 2010

ER -