Analyzing item features for cold-start problems in recommendation systems

Soryoung Kim, Sang Min Choi, Yo-Sub Han, Ka Lok Man, Kaiyu Wan

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

3 Citations (Scopus)

Abstract

With the development of web technologies, there is lots of information on the web. For effective web searching, the recommendation systems appear on the web. The recommendation systems provide customized information for the personal users. The conventional processes of the recommendation are generally based on the user preferences for the items. This leads to the cold-start problems for new items in recommending since new items have no user preferences. Although there are some studies to alleviate this problem by utilizing item features such as category information, the studies do not provide the validities of the use of item features. Namely, they just use the item features without analyzing features. If a feature draws meaningful recommendation results, there are some reasons that the feature can draw the results. We try to find these reasons. We calculate the uncertainty of item features by applying entropy in information theory and assume that this uncertainty of item features can show the level of reliability for the recommendation results. We verify our assumption by utilizing some tests in movie domain.

Original languageEnglish
Title of host publicationProceedings - 2014 10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2014
EditorsJunzo Watada, Akinori Ito, Chien-Ming Chen, Jeng-Shyang Pan, Han-Chieh Chao
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages167-170
Number of pages4
ISBN (Electronic)9781479953905
DOIs
Publication statusPublished - 2014 Jan 1
Event10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2014 - Kitakyushu, Japan
Duration: 2014 Aug 272014 Aug 29

Other

Other10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2014
CountryJapan
CityKitakyushu
Period14/8/2714/8/29

Fingerprint

Recommender systems
Information theory
Entropy
Uncertainty

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Artificial Intelligence
  • Signal Processing

Cite this

Kim, S., Choi, S. M., Han, Y-S., Man, K. L., & Wan, K. (2014). Analyzing item features for cold-start problems in recommendation systems. In J. Watada, A. Ito, C-M. Chen, J-S. Pan, & H-C. Chao (Eds.), Proceedings - 2014 10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2014 (pp. 167-170). [6998294] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IIH-MSP.2014.48
Kim, Soryoung ; Choi, Sang Min ; Han, Yo-Sub ; Man, Ka Lok ; Wan, Kaiyu. / Analyzing item features for cold-start problems in recommendation systems. Proceedings - 2014 10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2014. editor / Junzo Watada ; Akinori Ito ; Chien-Ming Chen ; Jeng-Shyang Pan ; Han-Chieh Chao. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 167-170
@inproceedings{21372337c1074e6d9aa6ac1def563485,
title = "Analyzing item features for cold-start problems in recommendation systems",
abstract = "With the development of web technologies, there is lots of information on the web. For effective web searching, the recommendation systems appear on the web. The recommendation systems provide customized information for the personal users. The conventional processes of the recommendation are generally based on the user preferences for the items. This leads to the cold-start problems for new items in recommending since new items have no user preferences. Although there are some studies to alleviate this problem by utilizing item features such as category information, the studies do not provide the validities of the use of item features. Namely, they just use the item features without analyzing features. If a feature draws meaningful recommendation results, there are some reasons that the feature can draw the results. We try to find these reasons. We calculate the uncertainty of item features by applying entropy in information theory and assume that this uncertainty of item features can show the level of reliability for the recommendation results. We verify our assumption by utilizing some tests in movie domain.",
author = "Soryoung Kim and Choi, {Sang Min} and Yo-Sub Han and Man, {Ka Lok} and Kaiyu Wan",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/IIH-MSP.2014.48",
language = "English",
pages = "167--170",
editor = "Junzo Watada and Akinori Ito and Chien-Ming Chen and Jeng-Shyang Pan and Han-Chieh Chao",
booktitle = "Proceedings - 2014 10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Kim, S, Choi, SM, Han, Y-S, Man, KL & Wan, K 2014, Analyzing item features for cold-start problems in recommendation systems. in J Watada, A Ito, C-M Chen, J-S Pan & H-C Chao (eds), Proceedings - 2014 10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2014., 6998294, Institute of Electrical and Electronics Engineers Inc., pp. 167-170, 10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2014, Kitakyushu, Japan, 14/8/27. https://doi.org/10.1109/IIH-MSP.2014.48

Analyzing item features for cold-start problems in recommendation systems. / Kim, Soryoung; Choi, Sang Min; Han, Yo-Sub; Man, Ka Lok; Wan, Kaiyu.

Proceedings - 2014 10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2014. ed. / Junzo Watada; Akinori Ito; Chien-Ming Chen; Jeng-Shyang Pan; Han-Chieh Chao. Institute of Electrical and Electronics Engineers Inc., 2014. p. 167-170 6998294.

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

TY - GEN

T1 - Analyzing item features for cold-start problems in recommendation systems

AU - Kim, Soryoung

AU - Choi, Sang Min

AU - Han, Yo-Sub

AU - Man, Ka Lok

AU - Wan, Kaiyu

PY - 2014/1/1

Y1 - 2014/1/1

N2 - With the development of web technologies, there is lots of information on the web. For effective web searching, the recommendation systems appear on the web. The recommendation systems provide customized information for the personal users. The conventional processes of the recommendation are generally based on the user preferences for the items. This leads to the cold-start problems for new items in recommending since new items have no user preferences. Although there are some studies to alleviate this problem by utilizing item features such as category information, the studies do not provide the validities of the use of item features. Namely, they just use the item features without analyzing features. If a feature draws meaningful recommendation results, there are some reasons that the feature can draw the results. We try to find these reasons. We calculate the uncertainty of item features by applying entropy in information theory and assume that this uncertainty of item features can show the level of reliability for the recommendation results. We verify our assumption by utilizing some tests in movie domain.

AB - With the development of web technologies, there is lots of information on the web. For effective web searching, the recommendation systems appear on the web. The recommendation systems provide customized information for the personal users. The conventional processes of the recommendation are generally based on the user preferences for the items. This leads to the cold-start problems for new items in recommending since new items have no user preferences. Although there are some studies to alleviate this problem by utilizing item features such as category information, the studies do not provide the validities of the use of item features. Namely, they just use the item features without analyzing features. If a feature draws meaningful recommendation results, there are some reasons that the feature can draw the results. We try to find these reasons. We calculate the uncertainty of item features by applying entropy in information theory and assume that this uncertainty of item features can show the level of reliability for the recommendation results. We verify our assumption by utilizing some tests in movie domain.

UR - http://www.scopus.com/inward/record.url?scp=84921652391&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921652391&partnerID=8YFLogxK

U2 - 10.1109/IIH-MSP.2014.48

DO - 10.1109/IIH-MSP.2014.48

M3 - Conference contribution

SP - 167

EP - 170

BT - Proceedings - 2014 10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2014

A2 - Watada, Junzo

A2 - Ito, Akinori

A2 - Chen, Chien-Ming

A2 - Pan, Jeng-Shyang

A2 - Chao, Han-Chieh

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kim S, Choi SM, Han Y-S, Man KL, Wan K. Analyzing item features for cold-start problems in recommendation systems. In Watada J, Ito A, Chen C-M, Pan J-S, Chao H-C, editors, Proceedings - 2014 10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 167-170. 6998294 https://doi.org/10.1109/IIH-MSP.2014.48