Finding trendy products from pins

Dingding Wang, Mitsunori Ogihara

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

Abstract

Fashion is a key defining factor of popular culture, and it changes over time. Each season tons of new products emerge to the market. People who follow fashion wish to discover new and trendy products and quickly catch the most fashionable styles. Traditionally, product trends can be found in fashion magazines and product catalogs, but now the proliferation of the Internet and social networks may have made trend e-discovery possible. This paper explores a novel problem of finding product trends through the posts on Pinterest, a rising social media for sharing interests using uploaded photographs and text comments. A weighted feature subset selection (WFSS) framework is applied to simultaneously group popular products into different types and select the most representative and discriminative terms to describe each product type. We compare WFSS with co-clustering algorithms, non-negative matrix factorization, and unsupervised feature selection methods. Experimental results on a data set collected from Pinterest show the effectiveness of WFSS in both product clustering and keyword selection.

Original languageEnglish (US)
Title of host publicationProceedings of the 2015 IEEE 9th International Conference on Semantic Computing, IEEE ICSC 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages428-431
Number of pages4
ISBN (Print)9781479979356
DOIs
StatePublished - Feb 26 2015
Event9th IEEE International Conference on Semantic Computing, IEEE ICSC 2015 - Anaheim, United States
Duration: Feb 7 2015Feb 9 2015

Other

Other9th IEEE International Conference on Semantic Computing, IEEE ICSC 2015
CountryUnited States
CityAnaheim
Period2/7/152/9/15

Fingerprint

Factorization
Clustering algorithms
Feature extraction
Internet

Keywords

  • finding trends
  • Pinterest
  • weighted feature subset selection

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Software

Cite this

Wang, D., & Ogihara, M. (2015). Finding trendy products from pins. In Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing, IEEE ICSC 2015 (pp. 428-431). [7050844] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICOSC.2015.7050844

Finding trendy products from pins. / Wang, Dingding; Ogihara, Mitsunori.

Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing, IEEE ICSC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 428-431 7050844.

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

Wang, D & Ogihara, M 2015, Finding trendy products from pins. in Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing, IEEE ICSC 2015., 7050844, Institute of Electrical and Electronics Engineers Inc., pp. 428-431, 9th IEEE International Conference on Semantic Computing, IEEE ICSC 2015, Anaheim, United States, 2/7/15. https://doi.org/10.1109/ICOSC.2015.7050844
Wang D, Ogihara M. Finding trendy products from pins. In Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing, IEEE ICSC 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 428-431. 7050844 https://doi.org/10.1109/ICOSC.2015.7050844
Wang, Dingding ; Ogihara, Mitsunori. / Finding trendy products from pins. Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing, IEEE ICSC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 428-431
@inproceedings{801d87ee2cdf4f43a5301a3ec8cb0d26,
title = "Finding trendy products from pins",
abstract = "Fashion is a key defining factor of popular culture, and it changes over time. Each season tons of new products emerge to the market. People who follow fashion wish to discover new and trendy products and quickly catch the most fashionable styles. Traditionally, product trends can be found in fashion magazines and product catalogs, but now the proliferation of the Internet and social networks may have made trend e-discovery possible. This paper explores a novel problem of finding product trends through the posts on Pinterest, a rising social media for sharing interests using uploaded photographs and text comments. A weighted feature subset selection (WFSS) framework is applied to simultaneously group popular products into different types and select the most representative and discriminative terms to describe each product type. We compare WFSS with co-clustering algorithms, non-negative matrix factorization, and unsupervised feature selection methods. Experimental results on a data set collected from Pinterest show the effectiveness of WFSS in both product clustering and keyword selection.",
keywords = "finding trends, Pinterest, weighted feature subset selection",
author = "Dingding Wang and Mitsunori Ogihara",
year = "2015",
month = "2",
day = "26",
doi = "10.1109/ICOSC.2015.7050844",
language = "English (US)",
isbn = "9781479979356",
pages = "428--431",
booktitle = "Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing, IEEE ICSC 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Finding trendy products from pins

AU - Wang, Dingding

AU - Ogihara, Mitsunori

PY - 2015/2/26

Y1 - 2015/2/26

N2 - Fashion is a key defining factor of popular culture, and it changes over time. Each season tons of new products emerge to the market. People who follow fashion wish to discover new and trendy products and quickly catch the most fashionable styles. Traditionally, product trends can be found in fashion magazines and product catalogs, but now the proliferation of the Internet and social networks may have made trend e-discovery possible. This paper explores a novel problem of finding product trends through the posts on Pinterest, a rising social media for sharing interests using uploaded photographs and text comments. A weighted feature subset selection (WFSS) framework is applied to simultaneously group popular products into different types and select the most representative and discriminative terms to describe each product type. We compare WFSS with co-clustering algorithms, non-negative matrix factorization, and unsupervised feature selection methods. Experimental results on a data set collected from Pinterest show the effectiveness of WFSS in both product clustering and keyword selection.

AB - Fashion is a key defining factor of popular culture, and it changes over time. Each season tons of new products emerge to the market. People who follow fashion wish to discover new and trendy products and quickly catch the most fashionable styles. Traditionally, product trends can be found in fashion magazines and product catalogs, but now the proliferation of the Internet and social networks may have made trend e-discovery possible. This paper explores a novel problem of finding product trends through the posts on Pinterest, a rising social media for sharing interests using uploaded photographs and text comments. A weighted feature subset selection (WFSS) framework is applied to simultaneously group popular products into different types and select the most representative and discriminative terms to describe each product type. We compare WFSS with co-clustering algorithms, non-negative matrix factorization, and unsupervised feature selection methods. Experimental results on a data set collected from Pinterest show the effectiveness of WFSS in both product clustering and keyword selection.

KW - finding trends

KW - Pinterest

KW - weighted feature subset selection

UR - http://www.scopus.com/inward/record.url?scp=84925620818&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84925620818&partnerID=8YFLogxK

U2 - 10.1109/ICOSC.2015.7050844

DO - 10.1109/ICOSC.2015.7050844

M3 - Conference contribution

SN - 9781479979356

SP - 428

EP - 431

BT - Proceedings of the 2015 IEEE 9th International Conference on Semantic Computing, IEEE ICSC 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -