Exploring demographic information in social media for product recommendation

Wayne Xin Zhao*, Sui Li, Yulan He, Liwei Wang, Ji-Rong Wen, Xiaoming Li

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

In many e-commerce Web sites, product recommendation is essential to improve user experience and boost sales. Most existing product recommender systems rely on historical transaction records or Web-site-browsing history of consumers in order to accurately predict online users’ preferences for product recommendation. As such, they are constrained by limited information available on specific e-commerce Web sites. With the prolific use of social media platforms, it now becomes possible to extract product demographics from online product reviews and social networks built from microblogs. Moreover, users’ public profiles available on social media often reveal their demographic attributes such as age, gender, and education. In this paper, we propose to leverage the demographic information of both products and users extracted from social media for product recommendation. In specific, we frame recommendation as a learning to rank problem which takes as input the features derived from both product and user demographics. An ensemble method based on the gradient-boosting regression trees is extended to make it suitable for our recommendation task. We have conducted extensive experiments to obtain both quantitative and qualitative evaluation results. Moreover, we have also conducted a user study to gauge the performance of our proposed recommender system in a real-world deployment. All the results show that our system is more effective in generating recommendation results better matching users’ preferences than the competitive baselines.

Original languageEnglish
Pages (from-to)61-89
Number of pages29
JournalKnowledge and Information Systems
Volume49
Issue number1
Early online date23 Oct 2015
DOIs
Publication statusPublished - Oct 2016

Fingerprint

Websites
Recommender systems
Gages
Sales
Education
History
Experiments

Bibliographical note

The final publication is available at Springer via http://dx.doi.org/10.1080/21552851.2015.1086557

Keywords

  • e-commerce
  • product demographic
  • product recommendation
  • social media

Cite this

Zhao, W. X., Li, S., He, Y., Wang, L., Wen, J-R., & Li, X. (2016). Exploring demographic information in social media for product recommendation. Knowledge and Information Systems, 49(1), 61-89. https://doi.org/10.1007/s10115-015-0897-5
Zhao, Wayne Xin ; Li, Sui ; He, Yulan ; Wang, Liwei ; Wen, Ji-Rong ; Li, Xiaoming. / Exploring demographic information in social media for product recommendation. In: Knowledge and Information Systems. 2016 ; Vol. 49, No. 1. pp. 61-89.
@article{33a56ca924e34de1923eaf5417fb7333,
title = "Exploring demographic information in social media for product recommendation",
abstract = "In many e-commerce Web sites, product recommendation is essential to improve user experience and boost sales. Most existing product recommender systems rely on historical transaction records or Web-site-browsing history of consumers in order to accurately predict online users’ preferences for product recommendation. As such, they are constrained by limited information available on specific e-commerce Web sites. With the prolific use of social media platforms, it now becomes possible to extract product demographics from online product reviews and social networks built from microblogs. Moreover, users’ public profiles available on social media often reveal their demographic attributes such as age, gender, and education. In this paper, we propose to leverage the demographic information of both products and users extracted from social media for product recommendation. In specific, we frame recommendation as a learning to rank problem which takes as input the features derived from both product and user demographics. An ensemble method based on the gradient-boosting regression trees is extended to make it suitable for our recommendation task. We have conducted extensive experiments to obtain both quantitative and qualitative evaluation results. Moreover, we have also conducted a user study to gauge the performance of our proposed recommender system in a real-world deployment. All the results show that our system is more effective in generating recommendation results better matching users’ preferences than the competitive baselines.",
keywords = "e-commerce, product demographic, product recommendation, social media",
author = "Zhao, {Wayne Xin} and Sui Li and Yulan He and Liwei Wang and Ji-Rong Wen and Xiaoming Li",
note = "The final publication is available at Springer via http://dx.doi.org/10.1080/21552851.2015.1086557",
year = "2016",
month = "10",
doi = "10.1007/s10115-015-0897-5",
language = "English",
volume = "49",
pages = "61--89",
number = "1",

}

Zhao, WX, Li, S, He, Y, Wang, L, Wen, J-R & Li, X 2016, 'Exploring demographic information in social media for product recommendation', Knowledge and Information Systems, vol. 49, no. 1, pp. 61-89. https://doi.org/10.1007/s10115-015-0897-5

Exploring demographic information in social media for product recommendation. / Zhao, Wayne Xin; Li, Sui; He, Yulan; Wang, Liwei; Wen, Ji-Rong; Li, Xiaoming.

In: Knowledge and Information Systems, Vol. 49, No. 1, 10.2016, p. 61-89.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Exploring demographic information in social media for product recommendation

AU - Zhao, Wayne Xin

AU - Li, Sui

AU - He, Yulan

AU - Wang, Liwei

AU - Wen, Ji-Rong

AU - Li, Xiaoming

N1 - The final publication is available at Springer via http://dx.doi.org/10.1080/21552851.2015.1086557

PY - 2016/10

Y1 - 2016/10

N2 - In many e-commerce Web sites, product recommendation is essential to improve user experience and boost sales. Most existing product recommender systems rely on historical transaction records or Web-site-browsing history of consumers in order to accurately predict online users’ preferences for product recommendation. As such, they are constrained by limited information available on specific e-commerce Web sites. With the prolific use of social media platforms, it now becomes possible to extract product demographics from online product reviews and social networks built from microblogs. Moreover, users’ public profiles available on social media often reveal their demographic attributes such as age, gender, and education. In this paper, we propose to leverage the demographic information of both products and users extracted from social media for product recommendation. In specific, we frame recommendation as a learning to rank problem which takes as input the features derived from both product and user demographics. An ensemble method based on the gradient-boosting regression trees is extended to make it suitable for our recommendation task. We have conducted extensive experiments to obtain both quantitative and qualitative evaluation results. Moreover, we have also conducted a user study to gauge the performance of our proposed recommender system in a real-world deployment. All the results show that our system is more effective in generating recommendation results better matching users’ preferences than the competitive baselines.

AB - In many e-commerce Web sites, product recommendation is essential to improve user experience and boost sales. Most existing product recommender systems rely on historical transaction records or Web-site-browsing history of consumers in order to accurately predict online users’ preferences for product recommendation. As such, they are constrained by limited information available on specific e-commerce Web sites. With the prolific use of social media platforms, it now becomes possible to extract product demographics from online product reviews and social networks built from microblogs. Moreover, users’ public profiles available on social media often reveal their demographic attributes such as age, gender, and education. In this paper, we propose to leverage the demographic information of both products and users extracted from social media for product recommendation. In specific, we frame recommendation as a learning to rank problem which takes as input the features derived from both product and user demographics. An ensemble method based on the gradient-boosting regression trees is extended to make it suitable for our recommendation task. We have conducted extensive experiments to obtain both quantitative and qualitative evaluation results. Moreover, we have also conducted a user study to gauge the performance of our proposed recommender system in a real-world deployment. All the results show that our system is more effective in generating recommendation results better matching users’ preferences than the competitive baselines.

KW - e-commerce

KW - product demographic

KW - product recommendation

KW - social media

UR - http://link.springer.com/article/10.1007%2Fs10115-015-0897-5

UR - http://www.scopus.com/inward/record.url?scp=84945156831&partnerID=8YFLogxK

U2 - 10.1007/s10115-015-0897-5

DO - 10.1007/s10115-015-0897-5

M3 - Article

AN - SCOPUS:84945156831

VL - 49

SP - 61

EP - 89

IS - 1

ER -

Zhao WX, Li S, He Y, Wang L, Wen J-R, Li X. Exploring demographic information in social media for product recommendation. Knowledge and Information Systems. 2016 Oct;49(1):61-89. https://doi.org/10.1007/s10115-015-0897-5