Abstract

With the great popularity of mobile devices, the amount of mobile apps has grown at a more dramatic rate than ever expected. A technical challenge is how to recommend suitable apps to mobile users. In this work, we identify and focus on a unique characteristic that exists in mobile app recommendation-That is, an app usually corresponds to multiple release versions. Based on this characteristic, we propose a fine-grain version-Aware app recommendation problem. Instead of directly learning the users' preferences over the apps, we aim to infer the ratings of users on a specific version of an app. However, the user-version rating matrix will be sparser than the corresponding user-App rating matrix, making existing recommendation methods less effective. In view of this, our approach has made two major extensions. First, we leverage the review text that is associated with each rating record; more importantly, we consider two types of versionbased correlations. The first type is to capture the temporal correlations between multiple versions within the same app, and the second type of correlation is to capture the aggregation correlations between similar apps. Experimental results on a large dataset demonstrate the superiority of our approach over several competitive methods.

Original languageEnglish (US)
Article number3015458
JournalACM Transactions on Information Systems
Volume35
Issue number4
DOIs
StatePublished - Jun 1 2017

Fingerprint

Application programs
Rating
Prediction
Mobile devices
Agglomeration

Keywords

  • App rating prediction
  • Recommender systems
  • Version correlation

ASJC Scopus subject areas

  • Information Systems
  • Business, Management and Accounting(all)
  • Computer Science Applications

Cite this

Version-Aware rating prediction for mobile app recommendation. / Yao, Yuan; Zhao, Wayne Xin; Wang, Yaojing; Tong, Hanghang; Xu, Feng; Lu, Jian.

In: ACM Transactions on Information Systems, Vol. 35, No. 4, 3015458, 01.06.2017.

Research output: Contribution to journalArticle

Yao, Yuan ; Zhao, Wayne Xin ; Wang, Yaojing ; Tong, Hanghang ; Xu, Feng ; Lu, Jian. / Version-Aware rating prediction for mobile app recommendation. In: ACM Transactions on Information Systems. 2017 ; Vol. 35, No. 4.
@article{683e1f58c0424d3fa0ebbc179cc35717,
title = "Version-Aware rating prediction for mobile app recommendation",
abstract = "With the great popularity of mobile devices, the amount of mobile apps has grown at a more dramatic rate than ever expected. A technical challenge is how to recommend suitable apps to mobile users. In this work, we identify and focus on a unique characteristic that exists in mobile app recommendation-That is, an app usually corresponds to multiple release versions. Based on this characteristic, we propose a fine-grain version-Aware app recommendation problem. Instead of directly learning the users' preferences over the apps, we aim to infer the ratings of users on a specific version of an app. However, the user-version rating matrix will be sparser than the corresponding user-App rating matrix, making existing recommendation methods less effective. In view of this, our approach has made two major extensions. First, we leverage the review text that is associated with each rating record; more importantly, we consider two types of versionbased correlations. The first type is to capture the temporal correlations between multiple versions within the same app, and the second type of correlation is to capture the aggregation correlations between similar apps. Experimental results on a large dataset demonstrate the superiority of our approach over several competitive methods.",
keywords = "App rating prediction, Recommender systems, Version correlation",
author = "Yuan Yao and Zhao, {Wayne Xin} and Yaojing Wang and Hanghang Tong and Feng Xu and Jian Lu",
year = "2017",
month = "6",
day = "1",
doi = "10.1145/3015458",
language = "English (US)",
volume = "35",
journal = "ACM Transactions on Information Systems",
issn = "1046-8188",
publisher = "Association for Computing Machinery (ACM)",
number = "4",

}

TY - JOUR

T1 - Version-Aware rating prediction for mobile app recommendation

AU - Yao, Yuan

AU - Zhao, Wayne Xin

AU - Wang, Yaojing

AU - Tong, Hanghang

AU - Xu, Feng

AU - Lu, Jian

PY - 2017/6/1

Y1 - 2017/6/1

N2 - With the great popularity of mobile devices, the amount of mobile apps has grown at a more dramatic rate than ever expected. A technical challenge is how to recommend suitable apps to mobile users. In this work, we identify and focus on a unique characteristic that exists in mobile app recommendation-That is, an app usually corresponds to multiple release versions. Based on this characteristic, we propose a fine-grain version-Aware app recommendation problem. Instead of directly learning the users' preferences over the apps, we aim to infer the ratings of users on a specific version of an app. However, the user-version rating matrix will be sparser than the corresponding user-App rating matrix, making existing recommendation methods less effective. In view of this, our approach has made two major extensions. First, we leverage the review text that is associated with each rating record; more importantly, we consider two types of versionbased correlations. The first type is to capture the temporal correlations between multiple versions within the same app, and the second type of correlation is to capture the aggregation correlations between similar apps. Experimental results on a large dataset demonstrate the superiority of our approach over several competitive methods.

AB - With the great popularity of mobile devices, the amount of mobile apps has grown at a more dramatic rate than ever expected. A technical challenge is how to recommend suitable apps to mobile users. In this work, we identify and focus on a unique characteristic that exists in mobile app recommendation-That is, an app usually corresponds to multiple release versions. Based on this characteristic, we propose a fine-grain version-Aware app recommendation problem. Instead of directly learning the users' preferences over the apps, we aim to infer the ratings of users on a specific version of an app. However, the user-version rating matrix will be sparser than the corresponding user-App rating matrix, making existing recommendation methods less effective. In view of this, our approach has made two major extensions. First, we leverage the review text that is associated with each rating record; more importantly, we consider two types of versionbased correlations. The first type is to capture the temporal correlations between multiple versions within the same app, and the second type of correlation is to capture the aggregation correlations between similar apps. Experimental results on a large dataset demonstrate the superiority of our approach over several competitive methods.

KW - App rating prediction

KW - Recommender systems

KW - Version correlation

UR - http://www.scopus.com/inward/record.url?scp=85021806966&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021806966&partnerID=8YFLogxK

U2 - 10.1145/3015458

DO - 10.1145/3015458

M3 - Article

AN - SCOPUS:85021806966

VL - 35

JO - ACM Transactions on Information Systems

JF - ACM Transactions on Information Systems

SN - 1046-8188

IS - 4

M1 - 3015458

ER -