Mobi-SAGE-RS: A sparse additive generative model-based mobile application recommender system

Hongzhi Yin, Weiqing Wang, Liang Chen, Xingzhong Du, Quoc Viet Hung Nguyen, Zi Huang

Research output: Contribution to journalArticleResearchpeer-review

Abstract

With the rapid prevalence of smart mobile devices and the dramatic proliferation of mobile applications (Apps), App recommendation becomes an emergent task that will benefit different stockholders of mobile App ecosystems. However, the extreme sparsity of user-App matrix and many newly emerging Apps create severe challenges, causing CF-based methods to degrade significantly in their recommendation performance. Besides, unlike traditional items, Apps have rights to access users’ personal resources (e.g., location, message and contact) which may lead to security risk or privacy leak. Thus, users’ choosing of Apps are influenced by not only their personal interests but also their privacy preferences. Moreover, user privacy preferences vary with App categories. In light of the above challenges, we propose a mobile sparse additive generative model (Mobi-SAGE) to recommend Apps by considering both user interests and category-aware user privacy preferences in this paper. To overcome the challenges from data sparsity and cold start, Mobi-SAGE exploits both textual and visual content associated with Apps to learn multi-view topics for user interest modeling. We collected a large-scale and real-world dataset from 360 App store - the biggest Android App platform in China, and conducted extensive experiments on it. The experimental results demonstrate that our Mobi-SAGE consistently and significantly outperforms the other existing state-of-the-art methods, which implies the importance of exploiting category-aware user privacy preferences and the multi-modal App content data on personalized App recommendation.

Original languageEnglish
Pages (from-to)68-80
Number of pages13
JournalKnowledge-Based Systems
Volume157
DOIs
Publication statusPublished - 1 Oct 2018
Externally publishedYes

Keywords

  • Cold start
  • Mobile applications
  • Privacy
  • Recommender system
  • Sparse additive generative model
  • User modeling

Cite this

Yin, Hongzhi ; Wang, Weiqing ; Chen, Liang ; Du, Xingzhong ; Hung Nguyen, Quoc Viet ; Huang, Zi. / Mobi-SAGE-RS : A sparse additive generative model-based mobile application recommender system. In: Knowledge-Based Systems. 2018 ; Vol. 157. pp. 68-80.
@article{d537eab2915e444c832751a4e63fce18,
title = "Mobi-SAGE-RS: A sparse additive generative model-based mobile application recommender system",
abstract = "With the rapid prevalence of smart mobile devices and the dramatic proliferation of mobile applications (Apps), App recommendation becomes an emergent task that will benefit different stockholders of mobile App ecosystems. However, the extreme sparsity of user-App matrix and many newly emerging Apps create severe challenges, causing CF-based methods to degrade significantly in their recommendation performance. Besides, unlike traditional items, Apps have rights to access users’ personal resources (e.g., location, message and contact) which may lead to security risk or privacy leak. Thus, users’ choosing of Apps are influenced by not only their personal interests but also their privacy preferences. Moreover, user privacy preferences vary with App categories. In light of the above challenges, we propose a mobile sparse additive generative model (Mobi-SAGE) to recommend Apps by considering both user interests and category-aware user privacy preferences in this paper. To overcome the challenges from data sparsity and cold start, Mobi-SAGE exploits both textual and visual content associated with Apps to learn multi-view topics for user interest modeling. We collected a large-scale and real-world dataset from 360 App store - the biggest Android App platform in China, and conducted extensive experiments on it. The experimental results demonstrate that our Mobi-SAGE consistently and significantly outperforms the other existing state-of-the-art methods, which implies the importance of exploiting category-aware user privacy preferences and the multi-modal App content data on personalized App recommendation.",
keywords = "Cold start, Mobile applications, Privacy, Recommender system, Sparse additive generative model, User modeling",
author = "Hongzhi Yin and Weiqing Wang and Liang Chen and Xingzhong Du and {Hung Nguyen}, {Quoc Viet} and Zi Huang",
year = "2018",
month = "10",
day = "1",
doi = "10.1016/j.knosys.2018.05.028",
language = "English",
volume = "157",
pages = "68--80",
journal = "Knowledge-Based Systems",
issn = "0950-7051",
publisher = "Elsevier",

}

Mobi-SAGE-RS : A sparse additive generative model-based mobile application recommender system. / Yin, Hongzhi; Wang, Weiqing; Chen, Liang; Du, Xingzhong; Hung Nguyen, Quoc Viet; Huang, Zi.

In: Knowledge-Based Systems, Vol. 157, 01.10.2018, p. 68-80.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Mobi-SAGE-RS

T2 - A sparse additive generative model-based mobile application recommender system

AU - Yin, Hongzhi

AU - Wang, Weiqing

AU - Chen, Liang

AU - Du, Xingzhong

AU - Hung Nguyen, Quoc Viet

AU - Huang, Zi

PY - 2018/10/1

Y1 - 2018/10/1

N2 - With the rapid prevalence of smart mobile devices and the dramatic proliferation of mobile applications (Apps), App recommendation becomes an emergent task that will benefit different stockholders of mobile App ecosystems. However, the extreme sparsity of user-App matrix and many newly emerging Apps create severe challenges, causing CF-based methods to degrade significantly in their recommendation performance. Besides, unlike traditional items, Apps have rights to access users’ personal resources (e.g., location, message and contact) which may lead to security risk or privacy leak. Thus, users’ choosing of Apps are influenced by not only their personal interests but also their privacy preferences. Moreover, user privacy preferences vary with App categories. In light of the above challenges, we propose a mobile sparse additive generative model (Mobi-SAGE) to recommend Apps by considering both user interests and category-aware user privacy preferences in this paper. To overcome the challenges from data sparsity and cold start, Mobi-SAGE exploits both textual and visual content associated with Apps to learn multi-view topics for user interest modeling. We collected a large-scale and real-world dataset from 360 App store - the biggest Android App platform in China, and conducted extensive experiments on it. The experimental results demonstrate that our Mobi-SAGE consistently and significantly outperforms the other existing state-of-the-art methods, which implies the importance of exploiting category-aware user privacy preferences and the multi-modal App content data on personalized App recommendation.

AB - With the rapid prevalence of smart mobile devices and the dramatic proliferation of mobile applications (Apps), App recommendation becomes an emergent task that will benefit different stockholders of mobile App ecosystems. However, the extreme sparsity of user-App matrix and many newly emerging Apps create severe challenges, causing CF-based methods to degrade significantly in their recommendation performance. Besides, unlike traditional items, Apps have rights to access users’ personal resources (e.g., location, message and contact) which may lead to security risk or privacy leak. Thus, users’ choosing of Apps are influenced by not only their personal interests but also their privacy preferences. Moreover, user privacy preferences vary with App categories. In light of the above challenges, we propose a mobile sparse additive generative model (Mobi-SAGE) to recommend Apps by considering both user interests and category-aware user privacy preferences in this paper. To overcome the challenges from data sparsity and cold start, Mobi-SAGE exploits both textual and visual content associated with Apps to learn multi-view topics for user interest modeling. We collected a large-scale and real-world dataset from 360 App store - the biggest Android App platform in China, and conducted extensive experiments on it. The experimental results demonstrate that our Mobi-SAGE consistently and significantly outperforms the other existing state-of-the-art methods, which implies the importance of exploiting category-aware user privacy preferences and the multi-modal App content data on personalized App recommendation.

KW - Cold start

KW - Mobile applications

KW - Privacy

KW - Recommender system

KW - Sparse additive generative model

KW - User modeling

UR - http://www.scopus.com/inward/record.url?scp=85047925681&partnerID=8YFLogxK

U2 - 10.1016/j.knosys.2018.05.028

DO - 10.1016/j.knosys.2018.05.028

M3 - Article

VL - 157

SP - 68

EP - 80

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

SN - 0950-7051

ER -