Inferring User Consumption Preferences from Social Media

Yang LI; Jing JIANG; Ting LIU

doi:10.1587/transinf.2016EDP7265

Inferring User Consumption Preferences from Social Media

Yang LI, Jing JIANG, Ting LIU

Full Text Views

0

Cite this

Summary :

Social Media has already become a new arena of our lives and involved different aspects of our social presence. Users' personal information and activities on social media presumably reveal their personal interests, which offer great opportunities for many e-commerce applications. In this paper, we propose a principled latent variable model to infer user consumption preferences at the category level (e.g. inferring what categories of products a user would like to buy). Our model naturally links users' published content and following relations on microblogs with their consumption behaviors on e-commerce websites. Experimental results show our model outperforms the state-of-the-art methods significantly in inferring a new user's consumption preference. Our model can also learn meaningful consumption-specific topics automatically.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.3 pp.537-545

Publication Date: 2017/03/01

Publicized: 2016/12/09

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016EDP7265

Type of Manuscript: PAPER

Category: Artificial Intelligence, Data Mining

Authors

Yang LI
  School of Computer Science and Technology, Harbin Institute of Technology
Jing JIANG
  Singapore Management University
Ting LIU
  School of Computer Science and Technology, Harbin Institute of Technology

Keyword

social media, e-commerce websites, consumption preferences, topic model

Cite this

Copy

Yang LI, Jing JIANG, Ting LIU, "Inferring User Consumption Preferences from Social Media" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 3, pp. 537-545, March 2017, doi: 10.1587/transinf.2016EDP7265.
Abstract: Social Media has already become a new arena of our lives and involved different aspects of our social presence. Users' personal information and activities on social media presumably reveal their personal interests, which offer great opportunities for many e-commerce applications. In this paper, we propose a principled latent variable model to infer user consumption preferences at the category level (e.g. inferring what categories of products a user would like to buy). Our model naturally links users' published content and following relations on microblogs with their consumption behaviors on e-commerce websites. Experimental results show our model outperforms the state-of-the-art methods significantly in inferring a new user's consumption preference. Our model can also learn meaningful consumption-specific topics automatically.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDP7265/_p

Copy

@ARTICLE{e100-d_3_537,
author={Yang LI, Jing JIANG, Ting LIU, },
journal={IEICE TRANSACTIONS on Information},
title={Inferring User Consumption Preferences from Social Media},
year={2017},
volume={E100-D},
number={3},
pages={537-545},
abstract={Social Media has already become a new arena of our lives and involved different aspects of our social presence. Users' personal information and activities on social media presumably reveal their personal interests, which offer great opportunities for many e-commerce applications. In this paper, we propose a principled latent variable model to infer user consumption preferences at the category level (e.g. inferring what categories of products a user would like to buy). Our model naturally links users' published content and following relations on microblogs with their consumption behaviors on e-commerce websites. Experimental results show our model outperforms the state-of-the-art methods significantly in inferring a new user's consumption preference. Our model can also learn meaningful consumption-specific topics automatically.},
keywords={},
doi={10.1587/transinf.2016EDP7265},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Inferring User Consumption Preferences from Social Media
T2 - IEICE TRANSACTIONS on Information
SP - 537
EP - 545
AU - Yang LI
AU - Jing JIANG
AU - Ting LIU
PY - 2017
DO - 10.1587/transinf.2016EDP7265
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2017
AB - Social Media has already become a new arena of our lives and involved different aspects of our social presence. Users' personal information and activities on social media presumably reveal their personal interests, which offer great opportunities for many e-commerce applications. In this paper, we propose a principled latent variable model to infer user consumption preferences at the category level (e.g. inferring what categories of products a user would like to buy). Our model naturally links users' published content and following relations on microblogs with their consumption behaviors on e-commerce websites. Experimental results show our model outperforms the state-of-the-art methods significantly in inferring a new user's consumption preference. Our model can also learn meaningful consumption-specific topics automatically.
ER -