Context-aware users' preference models by integrating real and supposed situation data

Chihiro Ono, Yasuhiro Takishima, Yoichi Motomura, Hideki Asoh, Yasuhide Shinagawa, Michita Imai, Yuichiro Anzai

研究成果: Article

4 引用 (Scopus)

抄録

This paper proposes a novel approach of constructing statistical preference models for context-aware personalized applications such as recommender systems. In constructing context-aware statistical preference models, one of the most important but difficult problems is acquiring a large amount of training data in various contexts/situations. In particular, some situations require a heavy workload to set them up or to collect subjects capable of answering the inquiries under those situations. Because of this difficulty, it is usually done to simply collect a small amount of data in a real situation, or to collect a large amount of data in a supposed situation, i.e., a situation that the subject pretends that he is in the specific situation to answer inquiries. However, both approaches have problems. As for the former approach, the performance of the constructed preference model is likely to be poor because the amount of data is small. For the latter approach, the data acquired in the supposed situation may differ from that acquired in the real situation. Nevertheless, the difference has not been taken seriously in existing researches. In this paper we propose methods of obtaining a better preference model by integrating a small amount of real situation data with a large amount of supposed situation data. The methods are evaluated using data regarding food preferences. The experimental results show that the precision of the preference model can be improved significantly.

元の言語English
ページ(範囲)2552-2559
ページ数8
ジャーナルIEICE Transactions on Information and Systems
E91-D
発行部数11
DOI
出版物ステータスPublished - 2008 11

Fingerprint

Recommender systems
Statistical Models

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

これを引用

Context-aware users' preference models by integrating real and supposed situation data. / Ono, Chihiro; Takishima, Yasuhiro; Motomura, Yoichi; Asoh, Hideki; Shinagawa, Yasuhide; Imai, Michita; Anzai, Yuichiro.

:: IEICE Transactions on Information and Systems, 巻 E91-D, 番号 11, 11.2008, p. 2552-2559.

研究成果: Article

Ono, Chihiro ; Takishima, Yasuhiro ; Motomura, Yoichi ; Asoh, Hideki ; Shinagawa, Yasuhide ; Imai, Michita ; Anzai, Yuichiro. / Context-aware users' preference models by integrating real and supposed situation data. :: IEICE Transactions on Information and Systems. 2008 ; 巻 E91-D, 番号 11. pp. 2552-2559.
@article{18fa11e75c0c4f908704a1b976d637e3,
title = "Context-aware users' preference models by integrating real and supposed situation data",
abstract = "This paper proposes a novel approach of constructing statistical preference models for context-aware personalized applications such as recommender systems. In constructing context-aware statistical preference models, one of the most important but difficult problems is acquiring a large amount of training data in various contexts/situations. In particular, some situations require a heavy workload to set them up or to collect subjects capable of answering the inquiries under those situations. Because of this difficulty, it is usually done to simply collect a small amount of data in a real situation, or to collect a large amount of data in a supposed situation, i.e., a situation that the subject pretends that he is in the specific situation to answer inquiries. However, both approaches have problems. As for the former approach, the performance of the constructed preference model is likely to be poor because the amount of data is small. For the latter approach, the data acquired in the supposed situation may differ from that acquired in the real situation. Nevertheless, the difference has not been taken seriously in existing researches. In this paper we propose methods of obtaining a better preference model by integrating a small amount of real situation data with a large amount of supposed situation data. The methods are evaluated using data regarding food preferences. The experimental results show that the precision of the preference model can be improved significantly.",
keywords = "Context-awareness, Probabilistic modeling, Recommender systems, User preference model",
author = "Chihiro Ono and Yasuhiro Takishima and Yoichi Motomura and Hideki Asoh and Yasuhide Shinagawa and Michita Imai and Yuichiro Anzai",
year = "2008",
month = "11",
doi = "10.1093/ietisy/e91-d.11.2552",
language = "English",
volume = "E91-D",
pages = "2552--2559",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "11",

}

TY - JOUR

T1 - Context-aware users' preference models by integrating real and supposed situation data

AU - Ono, Chihiro

AU - Takishima, Yasuhiro

AU - Motomura, Yoichi

AU - Asoh, Hideki

AU - Shinagawa, Yasuhide

AU - Imai, Michita

AU - Anzai, Yuichiro

PY - 2008/11

Y1 - 2008/11

N2 - This paper proposes a novel approach of constructing statistical preference models for context-aware personalized applications such as recommender systems. In constructing context-aware statistical preference models, one of the most important but difficult problems is acquiring a large amount of training data in various contexts/situations. In particular, some situations require a heavy workload to set them up or to collect subjects capable of answering the inquiries under those situations. Because of this difficulty, it is usually done to simply collect a small amount of data in a real situation, or to collect a large amount of data in a supposed situation, i.e., a situation that the subject pretends that he is in the specific situation to answer inquiries. However, both approaches have problems. As for the former approach, the performance of the constructed preference model is likely to be poor because the amount of data is small. For the latter approach, the data acquired in the supposed situation may differ from that acquired in the real situation. Nevertheless, the difference has not been taken seriously in existing researches. In this paper we propose methods of obtaining a better preference model by integrating a small amount of real situation data with a large amount of supposed situation data. The methods are evaluated using data regarding food preferences. The experimental results show that the precision of the preference model can be improved significantly.

AB - This paper proposes a novel approach of constructing statistical preference models for context-aware personalized applications such as recommender systems. In constructing context-aware statistical preference models, one of the most important but difficult problems is acquiring a large amount of training data in various contexts/situations. In particular, some situations require a heavy workload to set them up or to collect subjects capable of answering the inquiries under those situations. Because of this difficulty, it is usually done to simply collect a small amount of data in a real situation, or to collect a large amount of data in a supposed situation, i.e., a situation that the subject pretends that he is in the specific situation to answer inquiries. However, both approaches have problems. As for the former approach, the performance of the constructed preference model is likely to be poor because the amount of data is small. For the latter approach, the data acquired in the supposed situation may differ from that acquired in the real situation. Nevertheless, the difference has not been taken seriously in existing researches. In this paper we propose methods of obtaining a better preference model by integrating a small amount of real situation data with a large amount of supposed situation data. The methods are evaluated using data regarding food preferences. The experimental results show that the precision of the preference model can be improved significantly.

KW - Context-awareness

KW - Probabilistic modeling

KW - Recommender systems

KW - User preference model

UR - http://www.scopus.com/inward/record.url?scp=68749110711&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=68749110711&partnerID=8YFLogxK

U2 - 10.1093/ietisy/e91-d.11.2552

DO - 10.1093/ietisy/e91-d.11.2552

M3 - Article

AN - SCOPUS:68749110711

VL - E91-D

SP - 2552

EP - 2559

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 11

ER -